{
  "benchmark_line": "gamebench2",
  "comparability_tuples": [
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "balanced",
      "results_cut_id": "20260807_123334",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": "20260807_123334",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": "20260807_123334",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": "20260807_123334",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": "20260807_123334",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_kind": "overall"
    }
  ],
  "generated_at": "2026-08-07T12:33:34Z",
  "public_release_id": "gb2-20260807-e64919171e70",
  "results_cut_id": "gb2-20260807-e64919171e70",
  "rows": [
    {
      "admitted_plugins": 8,
      "attempted_matches": 712,
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.660969999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 84.62938089750429,
      "contributing_entrants": null,
      "distinct_rated_opponents": 326,
      "draws": 94,
      "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": 66.9670189086873,
      "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": 712,
      "rating_method": "sequential_elo",
      "raw_elo": 1840.6422584145396,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 84.62938089750429,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 502
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 894,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 2.09943,
        "mean": 1.379653125,
        "median": 1.3205149999999999,
        "min": 0.8875599999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 22.07445
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 80.80364109715514,
      "contributing_entrants": null,
      "distinct_rated_opponents": 396,
      "draws": 63,
      "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": 157,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 63.096152664379886,
      "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": 894,
      "rating_method": "sequential_elo",
      "raw_elo": 1827.251492052022,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 76.71614536377726,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 674
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1314,
      "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": 74.90272134044969,
      "contributing_entrants": null,
      "distinct_rated_opponents": 657,
      "draws": 176,
      "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": 233,
      "max_score": 95.74255598925224,
      "measured_at": null,
      "min_score": 44.983185125573506,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1314,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.1800960050937,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 72.44353093299611,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 905
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 698,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.140645
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 72.00166756452465,
      "contributing_entrants": null,
      "distinct_rated_opponents": 322,
      "draws": 136,
      "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": 119,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 31.89608232157542,
      "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": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.57144525601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 72.00166756452465,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 441
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1390,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 109,
      "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": 4.570125000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 69.63250431033174,
      "contributing_entrants": null,
      "distinct_rated_opponents": 691,
      "draws": 302,
      "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": "2026-08-05T05:33:21Z",
      "losses": 246,
      "max_score": 99.17317608622864,
      "measured_at": null,
      "min_score": 43.10391328842407,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1389,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.5745090558803,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 67.34634456096008,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 841
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 624,
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0372
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.6964642118633,
      "contributing_entrants": null,
      "distinct_rated_opponents": 310,
      "draws": 68,
      "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": 147,
      "max_score": 84.02163040431354,
      "measured_at": null,
      "min_score": 47.83931957227835,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 620,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.031207905637,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 66.44103633431087,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 405
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 700,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 12,
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 80.47395
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.26422692833881,
      "contributing_entrants": null,
      "distinct_rated_opponents": 323,
      "draws": 79,
      "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": 201,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 20.34202322749009,
      "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": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.1981625117858,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 66.26422692833881,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 420
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 637,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 48,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885474999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 67.14610422168701,
      "contributing_entrants": null,
      "distinct_rated_opponents": 302,
      "draws": 124,
      "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": 144,
      "max_score": 94.05837364506577,
      "measured_at": null,
      "min_score": 15.142060466906322,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.518116772612,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 64.94157743754894,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7,
      "attempted_matches": 658,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 14,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.449889999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 67.09931744185045,
      "contributing_entrants": null,
      "distinct_rated_opponents": 309,
      "draws": 83,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:23:19Z",
      "losses": 181,
      "max_score": 85.7032381321606,
      "measured_at": null,
      "min_score": 45.72757509137996,
      "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": 658,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.9652062921778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 64.89632675143649,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 714,
      "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-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 4.11992
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 58.665774525975536,
      "contributing_entrants": null,
      "distinct_rated_opponents": 357,
      "draws": 154,
      "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": 180,
      "max_score": 85.05033494665588,
      "measured_at": null,
      "min_score": 39.33968507396859,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 714,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.8401666025804,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 0.1111111111111111,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 56.96350162639645,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8,
      "attempted_matches": 708,
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.3280125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.51299956858802,
      "contributing_entrants": null,
      "distinct_rated_opponents": 332,
      "draws": 152,
      "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": 231,
      "max_score": 78.97727049438612,
      "measured_at": null,
      "min_score": 42.88844588724325,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 708,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.6847586482772,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 55.51299956858802,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 325
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 734,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 67,
      "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": 53.54328630060818,
      "contributing_entrants": null,
      "distinct_rated_opponents": 366,
      "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": "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": 187,
      "max_score": 93.17614952930187,
      "measured_at": null,
      "min_score": 19.20229853735902,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.4485540370158,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 53.54328630060818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 311
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 836,
      "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-2026-07-30": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.5087455999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.49184542328232,
      "contributing_entrants": null,
      "distinct_rated_opponents": 417,
      "draws": 192,
      "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": 247,
      "max_score": 80.48164573606203,
      "measured_at": null,
      "min_score": 30.44728628591251,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 834,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.5843011865277,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 53.49184542328232,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 395
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1054,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 53,
      "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": 53.090232750620466,
      "contributing_entrants": null,
      "distinct_rated_opponents": 528,
      "draws": 306,
      "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": "2026-08-05T06:55:12Z",
      "losses": 232,
      "max_score": 91.70201059215609,
      "measured_at": null,
      "min_score": 21.969050080927598,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1054,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.2160656754747,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 51.347185385006284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 516
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 714,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 78,
      "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-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.74852
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.74604881905605,
      "contributing_entrants": null,
      "distinct_rated_opponents": 351,
      "draws": 262,
      "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": 99.95680517171921,
      "measured_at": null,
      "min_score": 22.571342246704436,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 708,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.6063071993926,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 50.74604881905605,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 292
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 774,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 118,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.5428550000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.615805651408955,
      "contributing_entrants": null,
      "distinct_rated_opponents": 387,
      "draws": 253,
      "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": 222,
      "max_score": 68.86330432028504,
      "measured_at": null,
      "min_score": 31.14381674077765,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 774,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.2727402600594,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 50.615805651408955,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 698,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "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": 4.987857,
        "mean": 3.1645696249999995,
        "median": 3.0710854999999997,
        "min": 1.985613,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 28.806541
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 51.77671506081652,
      "contributing_entrants": null,
      "distinct_rated_opponents": 337,
      "draws": 156,
      "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": 234,
      "max_score": 81.11440057033718,
      "measured_at": null,
      "min_score": 15.787023585925473,
      "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": 698,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.1822393361529,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 0.1111111111111111,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 50.27433825612214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8,
      "attempted_matches": 742,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 59,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.98915
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.969059392457204,
      "contributing_entrants": null,
      "distinct_rated_opponents": 369,
      "draws": 235,
      "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": 200,
      "max_score": 95.42130277416098,
      "measured_at": null,
      "min_score": 23.285331416066995,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 740,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.0798981797777,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.969059392457204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 305
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 762,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 93,
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.97393
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.145924913466516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 380,
      "draws": 267,
      "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": 213,
      "max_score": 68.15920342920347,
      "measured_at": null,
      "min_score": 28.975930507597035,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.786339149516,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.145924913466516,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 388,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 47,
      "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-2026-07-30": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.6080262
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.11650001410064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 194,
      "draws": 221,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "2026-08-05T05:28:59Z",
      "losses": 171,
      "max_score": 68.5646741796879,
      "measured_at": null,
      "min_score": 20.180463665789603,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.1331996248375,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.11650001410064,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 9,
      "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-2026-07-30": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.5964052
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.0057833578023,
      "contributing_entrants": null,
      "distinct_rated_opponents": 156,
      "draws": 123,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "2026-08-05T05:37:07Z",
      "losses": 183,
      "max_score": 66.94474034970983,
      "measured_at": null,
      "min_score": 17.698293904601133,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 602,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.0476251439297,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.0057833578023,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 296
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 321,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 25,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.6549207,
        "mean": 0.4590043071428571,
        "median": 0.4757886,
        "min": 0.31911,
        "recorded_attempt_count": 37,
        "run_count": 12,
        "total": 5.4520296
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 51.250177289164334,
      "contributing_entrants": null,
      "distinct_rated_opponents": 161,
      "draws": 95,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": 4,
      "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:28:59Z",
      "losses": 145,
      "max_score": 74.49579059518622,
      "measured_at": null,
      "min_score": 42.77809618811668,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Google",
      "provider_key": "google",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 533,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.1334739346785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "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": "openrouter",
        "provider_setting_label": "High (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "High (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": 4,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 46.309762883848656,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 293
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 714,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.244315,
        "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": 45.72055502526362,
      "contributing_entrants": null,
      "distinct_rated_opponents": 356,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:11Z",
      "losses": 223,
      "max_score": 69.00313139343699,
      "measured_at": null,
      "min_score": 28.065418891234213,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 713,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.7871186649982,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 45.72055502526362,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 295
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 608,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 20,
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.262825
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.49013596853746,
      "contributing_entrants": null,
      "distinct_rated_opponents": 302,
      "draws": 157,
      "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": 187,
      "max_score": 66.52956277651462,
      "measured_at": null,
      "min_score": 22.761732969686722,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 608,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.9957511032885,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 44.96378159356898,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 807,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 56,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 2.0151682500000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.59159045145555,
      "contributing_entrants": null,
      "distinct_rated_opponents": 403,
      "draws": 250,
      "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": 247,
      "max_score": 62.06281243846746,
      "measured_at": null,
      "min_score": 25.554134372396923,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 805,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.0451461188634,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 44.59159045145555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 308
    },
    {
      "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-2026-07-30": 17
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 4.09607
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 44.226913968228395,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 388,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:23:03Z",
      "losses": 356,
      "max_score": 60.02072384999008,
      "measured_at": null,
      "min_score": 25.189542735608256,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1094,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.263075723822,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 43.51905494070913,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 350
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 758,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 106,
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.39147302621685,
      "contributing_entrants": null,
      "distinct_rated_opponents": 379,
      "draws": 297,
      "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": 203,
      "max_score": 83.06075814643916,
      "measured_at": null,
      "min_score": 20.525841154304743,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 758,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.4694399543237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 43.39147302621685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 258
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 770,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 109,
      "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": 0.046574000000000004,
        "mean": 0.036155625000000004,
        "median": 0.035338,
        "min": 0.025803,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 0.315048
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 44.28791315320453,
      "contributing_entrants": null,
      "distinct_rated_opponents": 385,
      "draws": 295,
      "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": 229,
      "max_score": 70.68540227201106,
      "measured_at": null,
      "min_score": 23.068325697614167,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 770,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.0247354322023,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 43.00283484393868,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 246
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 702,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.147405,
        "mean": 0.12146437500000001,
        "median": 0.124865,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.069485
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 44.076052399600464,
      "contributing_entrants": null,
      "distinct_rated_opponents": 347,
      "draws": 189,
      "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": 235,
      "max_score": 62.3891044858804,
      "measured_at": null,
      "min_score": 27.998655419890518,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.22877695441,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.79712153869371,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 272
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 626,
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.783799081191745,
      "contributing_entrants": null,
      "distinct_rated_opponents": 313,
      "draws": 157,
      "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": 222,
      "max_score": 65.54813103397758,
      "measured_at": null,
      "min_score": 26.534569513484524,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.866290235885,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.60662589311128,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 576,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 78,
      "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": 44.28286266599719,
      "contributing_entrants": null,
      "distinct_rated_opponents": 281,
      "draws": 132,
      "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": 242,
      "max_score": 71.11107962938964,
      "measured_at": null,
      "min_score": 23.61062430589122,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 576,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.0119875947578,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 41.20984717192794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 784,
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.3395199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.6213249858686,
      "contributing_entrants": null,
      "distinct_rated_opponents": 392,
      "draws": 287,
      "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": 250,
      "max_score": 54.85823075496087,
      "measured_at": null,
      "min_score": 26.523304025075756,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 784,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.6721469495028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.6213249858686,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1140,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 95,
      "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": 0.3591713804
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 40.619224127384456,
      "contributing_entrants": null,
      "distinct_rated_opponents": 570,
      "draws": 376,
      "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": 399,
      "max_score": 64.32999385511812,
      "measured_at": null,
      "min_score": 20.60128829346809,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1140,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.4359727217739,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.619224127384456,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 365
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 65,
      "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": 43.52384843515179,
      "contributing_entrants": null,
      "distinct_rated_opponents": 198,
      "draws": 198,
      "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": "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": 216,
      "max_score": 74.1617078908414,
      "measured_at": null,
      "min_score": 23.34842170383965,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.0488029127557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.503504840575566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 562,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 82,
      "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": 40.36964566822354,
      "contributing_entrants": null,
      "distinct_rated_opponents": 281,
      "draws": 225,
      "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": 160,
      "max_score": 69.68324241888193,
      "measured_at": null,
      "min_score": 22.919618819874938,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 562,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.9558617679427,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.36964566822354,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 724,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 92,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.6244280000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.52323884508071,
      "contributing_entrants": null,
      "distinct_rated_opponents": 362,
      "draws": 237,
      "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": 212,
      "max_score": 52.82357979001043,
      "measured_at": null,
      "min_score": 26.602617521323882,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 724,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.0733475614757,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.15995659275643,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 752,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 110,
      "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-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063374999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 40.807182043299505,
      "contributing_entrants": null,
      "distinct_rated_opponents": 372,
      "draws": 298,
      "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": 240,
      "max_score": 52.193541012565454,
      "measured_at": null,
      "min_score": 24.606530359301495,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.2289950075524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 39.6231022171695,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 212
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 44,
      "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-2026-07-30": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.5947035999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.417956094564275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 182,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "2026-08-05T05:36:22Z",
      "losses": 164,
      "max_score": 62.895170182688986,
      "measured_at": null,
      "min_score": 6.748867164434723,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.3840324485352,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 39.417956094564275,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 220
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 660,
      "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": 0.12449953100000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.574001935890315,
      "contributing_entrants": null,
      "distinct_rated_opponents": 324,
      "draws": 232,
      "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": "2026-08-05T04:18:01Z",
      "losses": 212,
      "max_score": 68.86134465387879,
      "measured_at": null,
      "min_score": 25.40534241954475,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 660,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.285671438715,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 39.24188483030178,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 72,
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.4205012499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.9368552071157,
      "contributing_entrants": null,
      "distinct_rated_opponents": 319,
      "draws": 173,
      "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": 248,
      "max_score": 63.54103500269817,
      "measured_at": null,
      "min_score": 21.462701167505323,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8592472486803,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.625656769040205,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 644,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 103,
      "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": 0.18239875000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.86320548854211,
      "contributing_entrants": null,
      "distinct_rated_opponents": 314,
      "draws": 211,
      "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": 223,
      "max_score": 66.08924139036272,
      "measured_at": null,
      "min_score": 25.366216398962596,
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6865413148555,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.554425102550525,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 548,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 37,
      "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": 39.644261976279005,
      "contributing_entrants": null,
      "distinct_rated_opponents": 271,
      "draws": 136,
      "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-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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:19:05Z",
      "losses": 199,
      "max_score": 51.181270461651444,
      "measured_at": null,
      "min_score": 29.295127175194555,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 548,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.1712755621945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.14552881709858,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 2,
      "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-2026-07-30": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 4.208937
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 41.34245113044162,
      "contributing_entrants": null,
      "distinct_rated_opponents": 99,
      "draws": 101,
      "eligibility_flag": true,
      "entry_count": 10,
      "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": [],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:28:45Z",
      "losses": 102,
      "max_score": 52.77796349718378,
      "measured_at": null,
      "min_score": 20.67238336600834,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.021787381488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.00705442729109,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1160,
      "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-2026-07-30": 25
        },
        "run_count": 16,
        "token_priced_attempt_count": 25,
        "total": 0.39544915
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 40.73000972203921,
      "contributing_entrants": null,
      "distinct_rated_opponents": 579,
      "draws": 221,
      "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": 492,
      "max_score": 65.72313807060283,
      "measured_at": null,
      "min_score": 15.418465089790947,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1158,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.948836258403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.903544958605444,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 445
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 359,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 28,
      "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-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.80503304728466,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 225,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": 268,
      "max_score": 68.24458515523042,
      "measured_at": null,
      "min_score": 16.47955768015164,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 734,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.1917047351317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.80503304728466,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 241
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 27,
      "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": 3.9126164999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.466137703026426,
      "contributing_entrants": null,
      "distinct_rated_opponents": 138,
      "draws": 148,
      "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-3.5-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": 193,
      "max_score": 77.64645353476814,
      "measured_at": null,
      "min_score": 13.591710349239374,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 520,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.9212423268102,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.657984375531065,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 37,
      "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": 40.3417006630155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 166,
      "draws": 125,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 221,
      "max_score": 69.21005238359456,
      "measured_at": null,
      "min_score": 19.841275546599956,
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 530,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.9071743566915,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.54218266144462,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 730,
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.374773927607926,
      "contributing_entrants": null,
      "distinct_rated_opponents": 361,
      "draws": 257,
      "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": 262,
      "max_score": 60.675097556373565,
      "measured_at": null,
      "min_score": 12.488827301220297,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 729,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.5692785326632,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.374773927607926,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 210
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 452,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 59,
      "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": 38.59132435668447,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 263,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": 244,
      "max_score": 63.10196361472715,
      "measured_at": null,
      "min_score": 20.826508924484237,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 730,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.7336760614942,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.324302104748774,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 384,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 6,
      "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": 40.076067521730096,
      "contributing_entrants": null,
      "distinct_rated_opponents": 192,
      "draws": 183,
      "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": "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": 221,
      "max_score": 53.725778913783415,
      "measured_at": null,
      "min_score": 22.092590644226938,
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 644,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.9528124625956,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.29498316942586,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 366,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 48,
      "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-2026-07-30": 16
        },
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 2.3233296000000005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.05266115739552,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 172,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "2026-08-05T06:56:50Z",
      "losses": 182,
      "max_score": 58.49270207782266,
      "measured_at": null,
      "min_score": 16.21094587734794,
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.3521597522176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.05266115739552,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1221,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 249,
      "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": 38.20459574532886,
      "contributing_entrants": null,
      "distinct_rated_opponents": 592,
      "draws": 415,
      "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": "2026-08-05T05:33:39Z",
      "losses": 415,
      "max_score": 52.594117482982824,
      "measured_at": null,
      "min_score": 25.188695148003053,
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1212,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.0190716655907,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.76028850836054,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 382
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 536,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 91,
      "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": 39.43599888199961,
      "contributing_entrants": null,
      "distinct_rated_opponents": 264,
      "draws": 149,
      "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": 217,
      "max_score": 69.71379024439247,
      "measured_at": null,
      "min_score": 24.5968014699668,
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.913477289564,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.699332183133805,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 91,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0222516,
        "mean": 0.01697319375,
        "median": 0.015739925000000002,
        "min": 0.012759,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.2715711
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.124225832861065,
      "contributing_entrants": null,
      "distinct_rated_opponents": 205,
      "draws": 390,
      "eligibility_flag": true,
      "entry_count": 30,
      "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": "2026-08-05T05:33:25Z",
      "losses": 330,
      "max_score": 60.72491770132335,
      "measured_at": null,
      "min_score": 18.932093277185512,
      "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": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1019,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.3812259706851,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.53004649639792,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 678,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 178,
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.374699430120664,
      "contributing_entrants": null,
      "distinct_rated_opponents": 335,
      "draws": 344,
      "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": 179,
      "max_score": 48.376451029853435,
      "measured_at": null,
      "min_score": 24.844878577648164,
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 678,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.5937919370792,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.147621152119854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 16,
      "attempted_matches": 498,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07826175,
        "mean": 0.05584070625,
        "median": 0.0541695,
        "min": 0.0411735,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.8934513000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.12279181493238,
      "contributing_entrants": null,
      "distinct_rated_opponents": 247,
      "draws": 473,
      "eligibility_flag": true,
      "entry_count": 32,
      "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": "2026-08-05T06:56:02Z",
      "losses": 344,
      "max_score": 49.20301710581384,
      "measured_at": null,
      "min_score": 18.71384108753165,
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1153,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.4543339404513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.12279181493238,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 336
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1120,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 144,
      "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-2026-07-30": 27
        },
        "run_count": 16,
        "token_priced_attempt_count": 27,
        "total": 0.14744575000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.33172325240589,
      "contributing_entrants": null,
      "distinct_rated_opponents": 552,
      "draws": 331,
      "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": 430,
      "max_score": 57.22166014466003,
      "measured_at": null,
      "min_score": 17.314483317000402,
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1114,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.9955615933582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 35.671687916445855,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 353
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 580,
      "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": 0.20304798
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.89690270596678,
      "contributing_entrants": null,
      "distinct_rated_opponents": 288,
      "draws": 133,
      "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": 224,
      "max_score": 51.404796674852406,
      "measured_at": null,
      "min_score": 20.685292976640326,
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 580,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.5217020426765,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 35.26704180309219,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 786,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:416a436309f013a4",
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840575,
        "min": 0.0773785,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 40.145487538652965,
      "contributing_entrants": null,
      "distinct_rated_opponents": 392,
      "draws": 122,
      "eligibility_flag": true,
      "entry_count": 38,
      "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": "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": "2026-08-05T06:56:02Z",
      "losses": 515,
      "max_score": 50.99483797073365,
      "measured_at": null,
      "min_score": 30.512771329112983,
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1183,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.6884393870807,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 35.24014138419697,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 546
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 902,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 107,
      "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": 37.71239433841487,
      "contributing_entrants": null,
      "distinct_rated_opponents": 451,
      "draws": 281,
      "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": 322,
      "max_score": 55.183064819125406,
      "measured_at": null,
      "min_score": 22.726527476576994,
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 902,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.0882010574696,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 34.34015744534528,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 60,
      "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": 34.04254490373653,
      "contributing_entrants": null,
      "distinct_rated_opponents": 247,
      "draws": 315,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": 290,
      "max_score": 51.82300342768883,
      "measured_at": null,
      "min_score": 23.203770649071114,
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 826,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3195565883266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 34.04254490373653,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6,
      "attempted_matches": 540,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 105,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.001632522,
        "mean": 0.00126739675,
        "median": 0.001232095,
        "min": 0.00090937,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010139174
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.02354942102359,
      "contributing_entrants": null,
      "distinct_rated_opponents": 264,
      "draws": 238,
      "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": 71.41435556334146,
      "measured_at": null,
      "min_score": 18.633293372543374,
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 534,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9282732895588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 33.523690133309174,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 86,
      "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": 0.030685472800000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.740610464060644,
      "contributing_entrants": null,
      "distinct_rated_opponents": 282,
      "draws": 129,
      "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": 258,
      "max_score": 55.72643086868543,
      "measured_at": null,
      "min_score": 16.856581427150502,
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 570,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.0776266239466,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 33.26038576513018,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 183
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 28,
      "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": 33.23436045013047,
      "contributing_entrants": null,
      "distinct_rated_opponents": 172,
      "draws": 153,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:20:31Z",
      "losses": 249,
      "max_score": 55.38133319989706,
      "measured_at": null,
      "min_score": 7.670088947709001,
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 600,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.5207692060533,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 33.23436045013047,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1408,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 288,
      "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": 34.086057407750324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 682,
      "draws": 512,
      "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": 521,
      "max_score": 51.81464157035592,
      "measured_at": null,
      "min_score": 13.631497595831043,
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1404,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.195016070938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.96695113357302,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 371
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1206,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 106,
      "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": 35.40708035253855,
      "contributing_entrants": null,
      "distinct_rated_opponents": 587,
      "draws": 380,
      "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": 491,
      "max_score": 63.27779754414018,
      "measured_at": null,
      "min_score": 15.88003173451959,
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1206,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.0330447282402,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.950001022690856,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 335
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 270,
      "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": 37.22399240106636,
      "contributing_entrants": null,
      "distinct_rated_opponents": 134,
      "draws": 74,
      "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": "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": [],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:57:18Z",
      "losses": 194,
      "max_score": 45.90001524707614,
      "measured_at": null,
      "min_score": 28.508028292488625,
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 436,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.3867339750273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.364092867730605,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 168
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 689,
      "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": 33.330776405133705,
      "contributing_entrants": null,
      "distinct_rated_opponents": 345,
      "draws": 312,
      "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": 238,
      "max_score": 42.11628633456594,
      "measured_at": null,
      "min_score": 25.98156528887542,
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 689,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.5211592810388,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.236467358124216,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 512,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 96,
      "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": 33.84070816163852,
      "contributing_entrants": null,
      "distinct_rated_opponents": 256,
      "draws": 172,
      "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": 205,
      "max_score": 53.84911215292571,
      "measured_at": null,
      "min_score": 13.294011760456632,
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 512,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5577122850716,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.779958466828784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:ad7736e5bdc3d28f",
      "capped_draws": 34,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.11484688800000001,
        "mean": 0.09513821700000001,
        "median": 0.094364214,
        "min": 0.07353490800000001,
        "recorded_attempt_count": 53,
        "run_count": 11,
        "total": 1.042744896
      },
      "codegen_evaluated_cells": 11,
      "conditional_success_score": 34.864150453423115,
      "contributing_entrants": null,
      "distinct_rated_opponents": 158,
      "draws": 112,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 7,
      "first_pass_rate": 0.6363636363636364,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "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": 198,
      "max_score": 52.16968167475123,
      "measured_at": null,
      "min_score": 17.49180460014081,
      "model_code_failure_rate": 0.36363636363636365,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.6363636363636364,
      "provider": "Other",
      "provider_key": "other",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 470,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.729255371479,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Enabled (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.139054799788628,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 92,
      "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": 35.535482548305495,
      "contributing_entrants": null,
      "distinct_rated_opponents": 239,
      "draws": 182,
      "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": 66.09501277916272,
      "measured_at": null,
      "min_score": 12.422397885640807,
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.9454948946295,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.679204262663337,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 178,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.004911942999999999,
        "mean": 0.0031858331662499998,
        "median": 0.002947833025,
        "min": 0.001831717,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.050973330659999996
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.58701354365491,
      "contributing_entrants": null,
      "distinct_rated_opponents": 511,
      "draws": 360,
      "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": 421,
      "max_score": 43.00749050094252,
      "measured_at": null,
      "min_score": 21.190773152388033,
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.4664548740934,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.549955352489913,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:dbac0d54294679dd",
      "capped_draws": 23,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 3,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "max": 0.729738,
        "mean": 0.551419875,
        "median": 0.531673125,
        "min": 0.39284850000000004,
        "recorded_attempt_count": 16,
        "run_count": 4,
        "total": 2.18593275
      },
      "codegen_evaluated_cells": 4,
      "conditional_success_score": 30.456487387328128,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 51,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 4,
      "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": "2026-08-05T05:05:45Z",
      "losses": 79,
      "max_score": 51.59820019792202,
      "measured_at": null,
      "min_score": 18.71804241712406,
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.5331890652135,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.456487387328128,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 110,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0597184625,
        "mean": 0.02467013555,
        "median": 0.0239011175,
        "min": 0.0040410944,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.19736108440000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.182546170823265,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 224,
      "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": 81,
      "max_score": 62.62712426295049,
      "measured_at": null,
      "min_score": 18.9315557741441,
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.560876806276,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.393059019139915,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 436,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 32,
      "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": 0.9722945000000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.00737150112073,
      "contributing_entrants": null,
      "distinct_rated_opponents": 218,
      "draws": 180,
      "eligibility_flag": true,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-05T06:56:50Z",
      "losses": 331,
      "max_score": 47.7133517329692,
      "measured_at": null,
      "min_score": 20.20823545772604,
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.1841731147554,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.98934399569381,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7,
      "attempted_matches": 452,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 45,
      "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": 0.21411433160000004
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 31.62821809235561,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 220,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": 37.4033081726625,
      "measured_at": null,
      "min_score": 23.324260913716756,
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 760,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.5618268820726,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.70219927295388,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6,
      "attempted_matches": 604,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 117,
      "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": 0.016532500000000002
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 30.588833048590292,
      "contributing_entrants": null,
      "distinct_rated_opponents": 294,
      "draws": 186,
      "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": "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": [],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:11Z",
      "losses": 253,
      "max_score": 44.46648998691777,
      "measured_at": null,
      "min_score": 14.548948613994082,
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 602,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.1894178321834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.43243623086199,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 16,
      "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": 30.623488700978687,
      "contributing_entrants": null,
      "distinct_rated_opponents": 158,
      "draws": 153,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": 285,
      "max_score": 54.06767438679486,
      "measured_at": null,
      "min_score": 9.407687981142418,
      "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": 632,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9811061129255,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.75865346487423,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 194
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 728,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 114,
      "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-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.1470525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.63144123682781,
      "contributing_entrants": null,
      "distinct_rated_opponents": 357,
      "draws": 336,
      "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": 261,
      "max_score": 39.705796487312476,
      "measured_at": null,
      "min_score": 10.185410895530666,
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 724,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.8559772496235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.63144123682781,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 30.62503365364087,
      "contributing_entrants": null,
      "distinct_rated_opponents": 196,
      "draws": 186,
      "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": 261,
      "max_score": 43.6188762763087,
      "measured_at": null,
      "min_score": 20.369345026768944,
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 632,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2196909932397,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.49980512824352,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 29,
      "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": 31.297397210158135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 116,
      "draws": 166,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 150,
      "max_score": 66.5532044937622,
      "measured_at": null,
      "min_score": 10.87785451326086,
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0840129537569,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 27.827758523316916,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 390,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 72,
      "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": 28.794662059114653,
      "contributing_entrants": null,
      "distinct_rated_opponents": 194,
      "draws": 366,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_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": "2026-08-05T05:35:16Z",
      "losses": 298,
      "max_score": 41.34256667887432,
      "measured_at": null,
      "min_score": 18.97110273604848,
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 838,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.0072427940133,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 27.109914524444687,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 644,
      "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": 28.950627058556446,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 160,
      "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": 323,
      "max_score": 49.375926945379035,
      "measured_at": null,
      "min_score": 1.18683615794815,
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 642,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.0438279595464,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 26.94159421474535,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 159
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 991,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 171,
      "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": 27.596471622289776,
      "contributing_entrants": null,
      "distinct_rated_opponents": 495,
      "draws": 378,
      "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": "2026-08-05T06:55:18Z",
      "losses": 411,
      "max_score": 45.4707813752063,
      "measured_at": null,
      "min_score": 19.262080807158373,
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 987,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.1766818118472,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 26.690430064939164,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 249,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 33,
      "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": 29.291490904881062,
      "contributing_entrants": null,
      "distinct_rated_opponents": 125,
      "draws": 74,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 255,
      "max_score": 42.140290158190794,
      "measured_at": null,
      "min_score": 15.139582069381618,
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 473,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.9007264410452,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 26.044227582746185,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 28,
      "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": 0.2720731754
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 28.50162445009465,
      "contributing_entrants": null,
      "distinct_rated_opponents": 211,
      "draws": 335,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": 271,
      "max_score": 48.61295183955477,
      "measured_at": null,
      "min_score": 12.01937572804176,
      "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": 748,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.3308152576674,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 25.754124959240865,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 86,
      "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": 26.078342532879816,
      "contributing_entrants": null,
      "distinct_rated_opponents": 316,
      "draws": 248,
      "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": 256,
      "max_score": 36.22574841026145,
      "measured_at": null,
      "min_score": 9.943666245746922,
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.5434369698607,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 25.222143870782425,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 51,
      "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": 0.5845103399999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.77665339720033,
      "contributing_entrants": null,
      "distinct_rated_opponents": 227,
      "draws": 240,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": 345,
      "max_score": 46.29733821571418,
      "measured_at": null,
      "min_score": 2.3222203559783994,
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.3301171841538,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.930359729410473,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 147
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 545,
      "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": 27.30904138637005,
      "contributing_entrants": null,
      "distinct_rated_opponents": 267,
      "draws": 175,
      "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": 252,
      "max_score": 42.83286645498502,
      "measured_at": null,
      "min_score": 8.83134021951195,
      "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": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 543,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.416172883214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.676504513388153,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 10,
      "attempted_matches": 1302,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 364,
      "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": 27.637609971091333,
      "contributing_entrants": null,
      "distinct_rated_opponents": 525,
      "draws": 662,
      "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": 433,
      "max_score": 40.20061892348984,
      "measured_at": null,
      "min_score": 19.463800160566905,
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1298,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.515121751544,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.573696377139072,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 48,
      "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": 25.05457754739122,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 127,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": "2026-08-05T05:12:01Z",
      "losses": 294,
      "max_score": 44.426727828824966,
      "measured_at": null,
      "min_score": 11.848074548273324,
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 531,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.850679973971,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.231990922169725,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 5,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.097374552,
        "mean": 0.068722872,
        "median": 0.085761432,
        "min": 0.023163,
        "recorded_attempt_count": 17,
        "run_count": 5,
        "total": 0.34361436
      },
      "codegen_evaluated_cells": 5,
      "conditional_success_score": 23.874622902161004,
      "contributing_entrants": null,
      "distinct_rated_opponents": 93,
      "draws": 71,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_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": 2,
      "first_pass_rate": 0.4,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:36:51Z",
      "losses": 176,
      "max_score": 44.424054904650205,
      "measured_at": null,
      "min_score": 9.884147887668306,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.7659667948435,
      "reasoning_bracket": "balanced",
      "reasoning_level": "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": 3,
      "repaired_rate": 0.6,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 23.874622902161004,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 83
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 413,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0456916,
        "mean": 0.031545040625,
        "median": 0.035551075,
        "min": 0.01864685,
        "recorded_attempt_count": 35,
        "run_count": 16,
        "total": 0.5047206500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.441305954041592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 207,
      "draws": 323,
      "eligibility_flag": true,
      "entry_count": 18,
      "evaluated_setting_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": 302,
      "max_score": 39.94026033234647,
      "measured_at": null,
      "min_score": 17.505656326341292,
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 783,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.3747431883885,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 23.76486806922119,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 9,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 39,
      "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": 27.236848647884678,
      "contributing_entrants": null,
      "distinct_rated_opponents": 157,
      "draws": 167,
      "eligibility_flag": true,
      "entry_count": 18,
      "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": "2026-08-05T05:37:42Z",
      "losses": 276,
      "max_score": 54.719235037247856,
      "measured_at": null,
      "min_score": 16.681032418541818,
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.1870983748304,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 23.58780284809997,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 241,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 27,
      "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": 25.66695092309063,
      "contributing_entrants": null,
      "distinct_rated_opponents": 121,
      "draws": 128,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 248,
      "max_score": 37.264518924471545,
      "measured_at": null,
      "min_score": 16.44510307833982,
      "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": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 469,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.1778899472356,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 22.821505172505795,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 11,
      "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": 24.379395262676457,
      "contributing_entrants": null,
      "distinct_rated_opponents": 150,
      "draws": 56,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_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": 302,
      "max_score": 39.53188452999624,
      "measured_at": null,
      "min_score": 5.696416759421026,
      "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": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.267011025682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 21.676688312409,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 719,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.038815,
        "mean": 0.02196775,
        "median": 0.0196975,
        "min": 0.016152,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.175742
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.928427773195263,
      "contributing_entrants": null,
      "distinct_rated_opponents": 352,
      "draws": 302,
      "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": 335,
      "max_score": 37.02321330902676,
      "measured_at": null,
      "min_score": 0.5457336893360095,
      "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": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 713,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.1105602032653,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 0.125,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 19.928427773195263,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5,
      "attempted_matches": 366,
      "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": 19.163277618622363,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "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": 208,
      "max_score": 46.321870346065246,
      "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": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.405759656805,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 17.038831009027934,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:72c37c305741dafa",
      "capped_draws": 4,
      "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-2026-07-30": 1
        },
        "run_count": 2,
        "token_priced_attempt_count": 3,
        "total": 0.939322
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 52.22657439455518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 80,
      "draws": 70,
      "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": "2026-08-05T02:54:54Z",
      "losses": 48,
      "max_score": 52.22657439455518,
      "measured_at": null,
      "min_score": 52.22657439455518,
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.8932580896576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 52.22657439455518,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 26,
      "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-2026-07-30": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 47.75501155028078,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 26,
      "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": "2026-08-05T05:27:30Z",
      "losses": 22,
      "max_score": 47.75501155028078,
      "measured_at": null,
      "min_score": 47.75501155028078,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.321654013368,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.75501155028078,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:763511c6e90215e4",
      "capped_draws": 66,
      "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-2026-07-30": 1
        },
        "recorded_attempt_count": 2,
        "run_count": 1,
        "total": 0.09014
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 44.83323249072341,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": 1,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "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": "2026-08-05T05:37:42Z",
      "losses": 10,
      "max_score": 44.83323249072341,
      "measured_at": null,
      "min_score": 44.83323249072341,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6057722063917,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 44.83323249072341,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:7c1742483386cdf8",
      "capped_draws": 4,
      "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": 42.15233778736079,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 21,
      "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": "2026-08-05T04:45:51Z",
      "losses": 18,
      "max_score": 42.15233778736079,
      "measured_at": null,
      "min_score": 42.15233778736079,
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.5781271742296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.15233778736079,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 37,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.026095300000000002,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.689134564680714,
      "contributing_entrants": null,
      "distinct_rated_opponents": 91,
      "draws": 55,
      "eligibility_flag": false,
      "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": "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": "2026-08-05T06:57:11Z",
      "losses": 124,
      "max_score": 61.23827813661711,
      "measured_at": null,
      "min_score": 22.033193461986272,
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.0006601656364,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.69265814945488,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 436,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 99,
      "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": 35.37784506240003,
      "contributing_entrants": null,
      "distinct_rated_opponents": 199,
      "draws": 107,
      "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": 44.576050565533166,
      "measured_at": null,
      "min_score": 23.94602226083568,
      "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": 401,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.1679734426546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.749103092373506,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 35,
      "wins": 124
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 406,
      "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": 0.31476170000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.73179707606592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 203,
      "draws": 149,
      "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": 160,
      "max_score": 41.79792203718302,
      "measured_at": null,
      "min_score": 26.292540253374842,
      "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": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6478697226069,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.205843656583273,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.215758025,
        "mean": 0.16162675,
        "median": 0.1594081875,
        "min": 0.098579625,
        "recorded_attempt_count": 36,
        "run_count": 16,
        "total": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.49125409606727,
      "contributing_entrants": null,
      "distinct_rated_opponents": 313,
      "draws": 291,
      "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": 193,
      "max_score": 59.024723737278265,
      "measured_at": null,
      "min_score": 21.874533667805792,
      "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": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.991222349984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.051332748112884,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:cceee2fda7208875",
      "capped_draws": 61,
      "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-2026-07-30": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.993705903564226,
      "contributing_entrants": null,
      "distinct_rated_opponents": 97,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-05T05:37:32Z",
      "losses": 134,
      "max_score": 44.1151076188509,
      "measured_at": null,
      "min_score": 24.102373476112174,
      "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": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.6231360847037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 27.744289020242476,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 403,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 70,
      "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": 31.222332345871024,
      "contributing_entrants": null,
      "distinct_rated_opponents": 202,
      "draws": 111,
      "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": "2026-08-05T05:29:13Z",
      "losses": 193,
      "max_score": 54.946552450271184,
      "measured_at": null,
      "min_score": 14.786907510390217,
      "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": 403,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.9727414911788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.432795454223083,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 26.689974102730307,
      "contributing_entrants": null,
      "distinct_rated_opponents": 129,
      "draws": 132,
      "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": "2026-08-05T05:35:50Z",
      "losses": 237,
      "max_score": 40.71668659092171,
      "measured_at": null,
      "min_score": 14.944434766576471,
      "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": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.052850804214,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 21.22575515545204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 534,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 192,
      "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": 25.767952587353744,
      "contributing_entrants": null,
      "distinct_rated_opponents": 245,
      "draws": 192,
      "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": 251,
      "max_score": 26.27689482403025,
      "measured_at": null,
      "min_score": 24.96235519414845,
      "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": 530,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.2155569895012,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 19.266038248032807,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 190,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 2,
      "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": 1.9149450000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.494721172537112,
      "contributing_entrants": null,
      "distinct_rated_opponents": 95,
      "draws": 19,
      "eligibility_flag": false,
      "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": "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": 257,
      "max_score": 32.00389460443945,
      "measured_at": null,
      "min_score": 14.583182450662427,
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.1309354872262,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 17.550366345371355,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 2000.7576930253301,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 46,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2000.7945640968424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 99.95680517171921,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 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": "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": 9,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1939.5874331556233,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 93.17614952930187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 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-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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1842.1038472104176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 83.08829242248612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 94,
      "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": 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-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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1821.051700392042,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 80.69363121403609,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "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": 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-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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.7971143350485,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 79.68193767817715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1799.055667309865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 78.50521178364832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-5-5:a77a9da79f1450e0",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.3774293727092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 73.2539994315327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 86,
      "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": 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-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": 25,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1753.8905307528914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 73.22615883803878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.1942513938784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.5069715162629,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.730117399782776,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.2538039468136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.41435556334146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 101,
      "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": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1719.3151008210912,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 70.20827359206642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.3768736235092947,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "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": 101,
      "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": 59,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.7127113138886,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.6194323591836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.975142627637888,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.0514577525005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.38623768514597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 2,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "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": "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": 10,
      "max_score": null,
      "measured_at": "2026-08-04T23:08:28Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.4010124412612,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.90936602956313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.61754645133582,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 28,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.1296139952278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 65.83747645882278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.1747525619378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.92984534569066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.7809463961355,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.096152664379886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.459772198068393,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.6640036153567,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.59904938707476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.375137598157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.9941304808233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.2596975548165,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.415585713195995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 2,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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-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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.793115128391,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.63498693048245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "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-5.4-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": 59,
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.4391919461466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.22166014466003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.383178954266332,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 54,
      "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": 47,
      "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": 109,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.5902539682866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 56.353504319456164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.9231294622796127,
      "unilateral_faults": 1,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": 35,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.8200827421863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.06767438679486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.056388861645896,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4078988417914,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.02675103959072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "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": 40,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.046272202658,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.84911215292571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "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": "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.0311336651146,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.58101009021854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 9,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T03:44:03Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.3359090209483,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.00989881361929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 55.00854884223441,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 38,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.2086367687052,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.82357979001043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.92650016324,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.61062123130229,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.642442208147656,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 46,
      "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": 35,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.7694478579945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.193541012565454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 11,
      "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": "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": 28,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.171019743832,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.9309965364074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 60,
      "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": 38,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.4553724122525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.404796674852406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 79,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.6020170542076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.46705421247383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.812711145915937,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "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": 113,
      "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": 102,
      "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": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.7215971564779,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.20338899029913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 78
    },
    {
      "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: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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.958621253768,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.990872009700986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 118,
      "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": 58,
      "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": 49,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.4048391771312,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.97125603147698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 90,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.5640194755229,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.376451029853435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 82,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:59Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.7086701736835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.082101410112614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.0601607140728,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:416a436309f013a4",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 61,
      "draws": 12,
      "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": "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": 67,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.7883171781857,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.90487405871482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 56.30417418419743,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:27:30Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.321654013368,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.75501155028078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "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": 40,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.3703249093664,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.751145429420006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.48795150977726,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 48,
      "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": 29,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.6320452094085,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.06768139295753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 81,
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.3948778945605,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.99357687265544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.5830662995282605,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "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": 1494.2465984289327,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.6739398929183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 124,
      "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": 60,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T04:18:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.5540474275292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.53770120402753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:15Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.5961376388414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.4707813752063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "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": 47,
      "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": 1492.718192054946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.419750227325316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": 1501.4383086612108,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.92433554994799,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.21328729190924,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:763511c6e90215e4",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:42Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6057722063917,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.83323249072341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8
    },
    {
      "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": 1483.4317022040432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.576050565533166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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: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": 57,
      "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": 38,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.4739373802697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.46648998691777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 50,
      "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": 56,
      "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": "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3529275927908,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.4397189219023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.245147965872874,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 47,
      "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": 44,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.4991443772221,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.61554479729633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "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": 52,
      "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": 1468.2228066206737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.00333801213897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 100,
      "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": 46,
      "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": 40,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.9188616540573,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.88844588724325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": 1482.9632959237965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.8706174363605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.014839042432094,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 46,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:59Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.2480909757069,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "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": "openrouter",
        "provider_setting_label": "High (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "High (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.77809618811668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.44733143012604,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "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": 1469.1718670852033,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.524252957277774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 25,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.8178118795715,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.428677925307234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": 52,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.9313234311355,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.21919853575708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.80422984590621,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "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": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:50Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.986338566357,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.10161283911572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 56.49112594673751,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "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": 1456.6726793206537,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.54726967322666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "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": "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": 28,
      "max_score": null,
      "measured_at": "2026-08-05T03:44:26Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.3773249800106,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.34256667887432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.81147465969834,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 308,
      "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": 122,
      "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": 114,
      "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": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.2355596845537,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.20061892348984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_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": 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": 1427.5356647847705,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.853074260758646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 240,
      "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": 114,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 93,
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.5389657970331,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.76737781757434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.74653294141069,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": 1421.2614381404182,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.19174966531355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 41,
      "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-3.6-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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.2915126707596,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.95822410059949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.101841152647836,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:06Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.060421397574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.04185705006656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 52.475044864937615,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "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",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:29:13Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8495385633466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.916500267983515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "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": 44,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.215360433307,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.877002635313595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "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": 1387.2340255103895,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.80720836897886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 92,
      "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": 49,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.025506422629,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.4805377654376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 80,
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.8120697560494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.05771191946257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.000430913942129,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 2,
      "distinct_rated_opponents": 31,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "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": 1382.3432162647712,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.194211118036264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.461325131721317,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "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": 1362.3304641440059,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.981232011417283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1351.2113457571206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.350197668676998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": 48,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.3506179183505,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.808038955158167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "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": "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:51:26Z",
      "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": 1366.1615915517368,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.575915709416066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.698553251899696,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:cceee2fda7208875",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 29,
      "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": "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.3403044689535,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.71108537090077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.36952453316905,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 24,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:42Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.9115333507139,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.898650929285388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.78635697673178,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": 1327.0032979772882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.9976913296341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.38386256637516,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "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": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.2462229301345,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.921401697168093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.5751600509567,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "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": 53,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.3826997250194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.676297098775773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "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": 104,
      "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": 101,
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.3132286826562,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.96235519414845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.817566863743322,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "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": 1303.4905060606818,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.261465808297835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.829266196477747,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "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": 1277.2755591791679,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.385721389270085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1251.9402308692768,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.9315557741441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1213.859923509973,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.88003173451959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 94,
      "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": 1213.8022511283734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.418465089790947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "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": 60,
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1232.3529714785363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.139582069381618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.406681034422945,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": 61,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.277071770066,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.583182450662427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 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": 1181.3686609045587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 11.482216539302486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 86,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1806.880102034298,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82,
      "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": 35,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.077401945733,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 82.05347374902418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 36,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.6468619133602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 75.80812316419362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 38,
      "draws": 30,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.47443747152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.88223492302193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 2,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "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": 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-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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.539453456156,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.99902750726241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "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": 89,
      "draws": 70,
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.5008318334221,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.15318329442692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 94
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "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": 72,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 15,
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.5328918965038,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.73552101088833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 35,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.5373124406053,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.21854400867016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.2699961396245,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.40569833085461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 76,
      "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": 38,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:42:13Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2391207094831,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.239355196944736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 36,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.4346988559294,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.54797454033727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-03T11:33:43Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.8610091385813,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.83057284966336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.89405657207563,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.7441141687189,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.456640462802426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 96,
      "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": 48,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.1232344259092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.44728628591251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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": "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0662350094012,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.2390924954411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 49,
      "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": "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.1585038473304,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.957237052457256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "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": "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.0331584380926,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.295127175194555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3389302620424,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.285703310875242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 74,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9783604804352,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.975930507597035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "draws": 57,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-03T10:38:54Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9276220539098,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.386103413880857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 30,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T01:19:10Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.262611968492,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.065418891234213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "draws": 56,
      "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": "2026-07-31T00:00:10Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2258908916226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.998655419890518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-04T20:03:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.6324167926382,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.610135698210527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "draws": 71,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.86953058894,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.753406537020762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.6607459565766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.523304025075756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "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": "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.647195989816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.292540253374842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84,
      "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": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.281346131285,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.98156528887542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 78,
      "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": 39,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.129902029356,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.578831533804646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "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": 45,
      "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": 1478.9493057309376,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.554134372396923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 86,
      "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": 43,
      "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": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.248896520903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.40534241954475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 122,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3006872699145,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.189542735608256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.355146918744417,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed: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": 51,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.448849917776,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.188695148003053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8084557546495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.844878577648164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 1482.8419989760441,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.513374734358962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "draws": 82,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.3176618766922,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.39608248464808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.8760079780336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.33755198695994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 44,
      "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": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4062283762817,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.06441481400451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 36,
      "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": 18,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 0,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.8163977249776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.741559061870756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "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": 86,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.396359014816,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.617486633688323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 54,
      "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": 2,
      "distinct_rated_opponents": 27,
      "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": 1489.1136087685727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.34842170383965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.47940711208657,
      "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: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": 41,
      "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": "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.1514124728146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.329211401413826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1093643154345,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.324260913716756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.35674892703957,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4974252789027,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.285331416066995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 2,
      "distinct_rated_opponents": 27,
      "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": 1485.6883786648543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.203770649071114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.992031574433888,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "draws": 82,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.565751019137,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.086494711467868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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-5.6-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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.5711246807089,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.068325697614167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.0532689115892,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.96981343482104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 31,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.841977949159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.919618819874938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 1470.3374865351009,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.761732969686722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64,
      "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": 32,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2125218481146,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.726527476576994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84,
      "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": 41,
      "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",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.3031221858107,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.571342246704436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 51,
      "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": 1459.7462631719882,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.380386424640683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58,
      "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": 2,
      "distinct_rated_opponents": 29,
      "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": "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": 22,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.889844365115,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.092590644226938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.156172217111,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.969050080927598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 88,
      "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": 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": "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2953460829026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.883388248077022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1464.2426317683783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.874533667805792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 92,
      "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": 4,
      "distinct_rated_opponents": 46,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.4225165190696,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.730603422049168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.99767510501163,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "draws": 70,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.4359726589596,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.690874544258786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 132,
      "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": 66,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.7374764232438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.190773152388033,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.355146918744417,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "draws": 82,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.8304846432588,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.826508924484237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.97128781498596,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed: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": 1462.4496711139095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.685292976640326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 55,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:41Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.198212620904,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.67238336600834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "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": 63,
      "draws": 117,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 8,
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.2688292024814,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.60128829346809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.755723064737715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "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": 1459.9363913520322,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.525841154304743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20,
      "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": 2,
      "distinct_rated_opponents": 10,
      "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-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": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:32Z",
      "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": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.0646270829602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.20823545772604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.15840602663853,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "draws": 74,
      "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": 6,
      "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": "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.8090974764614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.180463665789603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.491466493865985,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 56,
      "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": 4,
      "distinct_rated_opponents": 28,
      "draws": 114,
      "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": 7,
      "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": "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.721647002374,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.22178430751722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.645487332256415,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 34,
      "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": 4,
      "distinct_rated_opponents": 16,
      "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": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.2086713176134,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.97110273604848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 58.88055773359793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 56,
      "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": 4,
      "distinct_rated_opponents": 28,
      "draws": 115,
      "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": 5,
      "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": "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.9288912413258,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.71384108753165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.19324853318743,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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": "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.0917807935598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.633293372543374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 2,
      "distinct_rated_opponents": 8,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:36Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2765108129372,
      "reasoning_bracket": "balanced",
      "reasoning_level": "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.40784673510266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 63.30774080334622,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "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": 4,
      "distinct_rated_opponents": 33,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 16,
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.8422251646493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.505656326341292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.718082484234934,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 2,
      "distinct_rated_opponents": 7,
      "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": "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": 2,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:19Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.565459593351,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.681032418541818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 61.8994692631296,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 57,
      "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": 15,
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.47622141143,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.47955768015164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.89405657207563,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "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": 2,
      "distinct_rated_opponents": 12,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.647858481688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.21094587734794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 78.125,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "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": 44,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T01:19:37Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.9368942846404,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.944434766576471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.89801750319316,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": 1445.3018284688678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.643544255379368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.996324165557496,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "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": 2,
      "distinct_rated_opponents": 19,
      "draws": 37,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:25Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.8982190001293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.54676360453859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.15703845127177,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "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": 2,
      "distinct_rated_opponents": 15,
      "draws": 43,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:46Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.9602022628883,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 11.233180622648142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.05265101338746,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 14,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.6077181148798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 10.87785451326086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.812854461075986,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "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": 2,
      "distinct_rated_opponents": 14,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.1191021856469,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 9.407687981142418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 2,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 112,
      "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": 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-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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1886.5839666583847,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 98.38502694069997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "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": 79,
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1861.0033303173484,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 95.74255598925224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 30,
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.3473191690596,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 70.49045424400458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 29,
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.3799977137346,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.90485555225239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 2,
      "distinct_rated_opponents": 19,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 15,
      "max_score": null,
      "measured_at": "2026-08-03T13:45:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.7566230465538,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.24738547213113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.80145244019624,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 40,
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.3083636563829,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 56.324293275397885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "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": "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:48Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.1778209283398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.946552450271184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "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": 86,
      "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-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": 54,
      "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.1482186314154,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.09590571829045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.866254227491025,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 27,
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.7107585816805,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.47594525860797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:72c37c305741dafa",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "draws": 70,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T02:54:54Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.8932580896576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.22657439455518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.866089496389785,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "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": 1571.8753694864479,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.11619311992135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58,
      "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": 29,
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.0279839646837,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.42280040640819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 81,
      "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": 40,
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.3839322567405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.35305938673562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "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": "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.872973253256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.893839142278445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.180010894095469,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "draws": 27,
      "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": 30,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.8397181307937,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.74207105225406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 13,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-03T14:16:22Z",
      "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": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.952914842092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "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": "openrouter",
        "provider_setting_label": "High (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "High (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.72105372304396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 76.23752243246881,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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-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": 23,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.7262366492885,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.55730234033761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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-4-5",
        "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.8257098927816,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.90185636252289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 27,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:27Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.2159632399143,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.89856102744325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.51471483712608,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:02Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.527697651422,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.87527093406364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 67.84523726457948,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 34,
      "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-3.6-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": 38,
      "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": "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.0142504521068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.34197525944053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.07360537523139,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "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": 1524.4985638630642,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.00749050094252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 88,
      "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": 44,
      "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-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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.3524419563448,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.304281381765435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:7c1742483386cdf8",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 21,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:51Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.5781271742296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.15233778736079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "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": 17,
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.2929924323498,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.38069259504271,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 1504.1234121905509,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.26204320265185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 83,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 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-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": 20,
      "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": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5548858435868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.63707357709248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1484.2886571135925,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.23648244618929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 56,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 32,
      "max_score": null,
      "measured_at": "2026-07-31T01:34:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.9632361068366,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.18649842669409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.507220868368073,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 25,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.8755147233076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.18446384616218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.7237122491786,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.860150083019626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "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": "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.3273441827764,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.494654124976805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.38178527761111,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 37,
      "draws": 37,
      "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": 18,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.915508520607,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.02321330902676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 24,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:57Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.6478351806873,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.83416050750126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 64.63816275334686,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:ad7736e5bdc3d28f",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 22,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:36:36Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.1284962693098,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Enabled (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.51286102183472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 57.12334745656489,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.1084595149894,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.328921102635334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 95,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 36,
      "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": "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": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.4996298826736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.83800371361828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.11749113942453,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 78,
      "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": "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": 46,
      "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": "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.8627401134768,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.72130392267117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.7223548257912,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 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-5.5",
        "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": 26,
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.647103601243,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.64775037461809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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": "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2133962405546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.28541772823972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 24,
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.199816272659,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.27444521040391,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-05T03:54:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.3589845100641,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.0378996400634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.241069098968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.513954746621025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 31,
      "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": 14,
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.3899699523217,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.476184640834816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 9
    },
    {
      "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": 1449.778133454939,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.26904479710366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 60,
      "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": 29,
      "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": 24,
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7947632570085,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.89608232157542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 2,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 26,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.3175616005683,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.88151024956463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.117366605781385,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 27,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.523896395089,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.578832477807513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 24,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.39286064408,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.388151856713836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 37,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3708349548044,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.35664793074286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:o3:416a436309f013a4",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 20,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-08-04T23:02:00Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9889629953232,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.228907975804475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.8044725589981,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.0068426521739,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.880698337056444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 34,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.7975158584218,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.81671727920589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 31,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.7587628203037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.549441181835455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T02:45:49Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.6395980970199,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.960074596473827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.76542547285167,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "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": 2,
      "distinct_rated_opponents": 18,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3307063559512,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.900297866687094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.86916081526379,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 13,
      "draws": 13,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-03T13:23:14Z",
      "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": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6154597021434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.873359195800802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 76.23752243246881,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "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": "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": 37,
      "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": "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8740419822784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.182519323216006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 31,
      "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": 11,
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.255627323167,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.171925207422163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 2,
      "distinct_rated_opponents": 13,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 11,
      "max_score": null,
      "measured_at": "2026-08-03T13:23:39Z",
      "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": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.401197179736,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.936698930432165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 76.23752243246881,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 33,
      "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": 26,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.5349424095307,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.175958376626816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 77,
      "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": 51,
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.7672192302994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.14500345598673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.493504750482622,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 29,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 26,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5010278143418,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.836159834589736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.941634169259466,
      "unilateral_faults": 1,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 14,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T13:44:40Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4311400458312,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.677879816109012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.15132550669373,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 24,
      "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": "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.2361193788938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.69906909498186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 29,
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.28947900497,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.516168554327326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.3895422530882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.46366360644326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.9748824540438,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.666335927907475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 35
    },
    {
      "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": 27,
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.1613620278795,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.428307136703403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.19324853318743,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:26:19Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.7495647402448,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.15319521590135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.07227218399459,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 31,
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.726476188212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.787023585925473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T02:39:33Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.9018046900726,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 6.748867164434723,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.551153208577354,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 44,
      "draws": 17,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1865.823673582791,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 76
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "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": 71,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.096473051806,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 79.47342462976314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.818262520573185,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 43,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.1290756470048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.74991968984401,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 42,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.5726584504935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.01517252922639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 41,
      "draws": 35,
      "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": "2026-08-05T01:54:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.201730875163,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.68784123456057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T03:43:28Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.589788462788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.71458862728154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.41912513169022,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 20,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:16Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.1157826110739,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "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": "openrouter",
        "provider_setting_label": "High (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "High (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.31339478971633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "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": "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": 22,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.3561576652844,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.225562918867894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1582.9690692214492,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.83931957227835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 96,
      "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": 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-5.4-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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.996519212638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.26997029285312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "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": 99,
      "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-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": 55,
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.8056788345384,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.983185125573506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "draws": 41,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.9585279553617,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.4786439895316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 31
    },
    {
      "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": 1561.7564985722227,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.441938728209706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "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": 49,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 15,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.148668508276,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.737382109924624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "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": 99,
      "draws": 79,
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.461981055621,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.10391328842407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "draws": 48,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8865414749796,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.16676257859201,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60,
      "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": 2,
      "distinct_rated_opponents": 30,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-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": 22,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.320457917925,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.0964147057753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.51693271964983,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.4112566798308,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.33968507396859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 48,
      "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": "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.4271477634718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.89921383372028,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T03:59:31Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.7252140790329,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.462569717437304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.89405657207563,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 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-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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.1627836273447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.25696174455382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0428742199645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.01257007858806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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-5.4",
        "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": 13,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.4148214952497,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.31932420897261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 48,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.170150760798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.94559731506889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1509.0423085525442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.50597954900976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "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": 44,
      "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": "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": 4,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6208754393567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.157939951088196,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.5599956004069,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.952233073927275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 165,
      "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": 82,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 19,
      "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": "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": 161,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.413996997494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.665436329086305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.879781663776944,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed: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": 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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:33:25Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.113459457968,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.35713798385482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 148,
      "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": 74,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.714578014611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.73976498521204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.124241049220077,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:03:31Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.669383234101,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.67442303505885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 17
    },
    {
      "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": 1502.1064415265755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.47394764651104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60,
      "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": 30,
      "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": "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.4747006526225,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.34819561268509,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7
    },
    {
      "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": 1501.1308285615892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.1670764313632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 108,
      "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": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.922495957919,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.866644636143132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 46,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.875178692428,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.726131179809055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 86,
      "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": 42,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.3691141009099,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.480599265900732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 100,
      "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": 50,
      "draws": 70,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.2760299875736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.478769660606087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82,
      "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": 40,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 24,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.3136234631593,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.466665424316382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 16
    },
    {
      "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": 1490.9532680536443,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.313916897298004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 88,
      "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": 43,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5133398135404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.231477991886752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 1486.0440995567778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.14381674077765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 140,
      "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": 70,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 9,
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.2045172936457,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.78875211304417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 21
    },
    {
      "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": 52,
      "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": 1483.6856058732603,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.749828609175978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 52,
      "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": 1481.537434054386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.39355816481966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 86,
      "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": 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-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": "2026-08-05T05:33:21Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.0322829267293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.965940546014295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 181,
      "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": 91,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 181,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.8442918018895,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.85012509642266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.417462425705285,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "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": 110,
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.5436102353326,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.621503848227775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.61455287691689,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 2,
      "distinct_rated_opponents": 32,
      "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": 7,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.5080466753927,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.43239275691567,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.37120607977092,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 2,
      "distinct_rated_opponents": 32,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.3790983677727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.91029406876563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.302124119453637,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 46,
      "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": "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0635006450743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.853421449925953,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 38,
      "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": 4,
      "distinct_rated_opponents": 19,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 16,
      "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": "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": 97,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.8762960785205,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.82991502575947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 57.47663899604805,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "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": 1482.6080624665635,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.801808670018016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56,
      "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": 2,
      "distinct_rated_opponents": 27,
      "draws": 73,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8974532015468,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.508028292488625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.21770585958794,
      "unilateral_faults": 2,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "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": 21,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.516457423049,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.397881427239696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "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": 86,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.096664771153,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.247391403906573,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 21,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T03:21:33Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.8183597556254,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.063919114389087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 58.92436501994144,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-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": 15,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.7557500321805,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.82354680882762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 34,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1281441770377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.51487556975524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "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": 1469.2709415655665,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.37461139902881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 64,
      "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": 2,
      "distinct_rated_opponents": 32,
      "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": 1485.0261871880703,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.287196375393837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.778097636226576,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "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": 48,
      "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": 1465.1792260115858,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.134886304266157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62,
      "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": 2,
      "distinct_rated_opponents": 31,
      "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": 1478.8701073233942,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.00641053588233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.014839042432094,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.1059463245633,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.709033756995762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 44,
      "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": 1463.6610917058263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.534569513484524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44,
      "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": 4,
      "distinct_rated_opponents": 22,
      "draws": 102,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.3216445459439,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.53021032625603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.60557679671052,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "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": 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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:16:32Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2020263508612,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.82750955564381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.290722098573895,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "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": 2,
      "distinct_rated_opponents": 14,
      "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": "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": 7,
      "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": "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.55224106402,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.564742978629265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.78635697673178,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "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": 4,
      "distinct_rated_opponents": 54,
      "draws": 127,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.549698354746,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.20314063680759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.151170782950608,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 2,
      "distinct_rated_opponents": 32,
      "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": 1461.3622341881628,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.4947403350086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.290722098573895,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 12,
      "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": "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9386277122185,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.36619296619383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3927996249965,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.3413516403082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.716708587278752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.61757338116737,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9324472888316,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.596644926517598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.353922850699,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.753586194664617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "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": 4,
      "distinct_rated_opponents": 41,
      "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": "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": 32,
      "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 3.5 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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.65523885426,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.162958277021243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 59.44850826147155,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "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": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:10:34Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7167570727886,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.941506078017632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.300442572851765,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.5187890361944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.693442822538298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 22,
      "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": "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.4106272254921,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.33720025505064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.325478923423304,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.4364488018932,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.444697310565857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.74828632574542,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": 37,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.573033769448,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.838331311955223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-6-flash:dbac0d54294679dd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "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": "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": 28,
      "max_score": null,
      "measured_at": "2026-08-05T04:05:34Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2638702081008,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.71804241712406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.28203845127178,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T01:11:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.7399927678175,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.698293904601133,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.393187298490844,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meituan-longcat-2-0:ad7736e5bdc3d28f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 45,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.0016320932775,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Enabled (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.49180460014081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.89090835978349,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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": 33,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.941773211182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.142060466906322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "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": 2,
      "distinct_rated_opponents": 17,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-04T21:56:09Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.114574817395,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 11.848074548273324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 55.86164620406626,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "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": 1376.1312280226116,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 9.943666245746922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 24,
      "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": 12,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T03:21:22Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.808512324239,
      "reasoning_bracket": "balanced",
      "reasoning_level": "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 9.884147887668306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 56.49112594673751,
      "unilateral_faults": 2,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "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": 37,
      "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 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.47949608107,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 7.670088947709001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.812854461075986,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2032.5608459804337,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 92.49362898125582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 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-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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 2007.5728572044336,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 90.25579059650316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "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": 115,
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1965.1031344087517,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 86.53651167123698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 206
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.9846191205747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.20269021147601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 114
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "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": 111,
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.5280885728605,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 82.07879945591797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 20,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1913.7523653539108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 81.36228215819001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.1338387843662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.11107962938964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "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": 72,
      "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": 39,
      "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": "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.5063962519441,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.90020433563501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.5579433554326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.38417347397768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 96,
      "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": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 30,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1733.9891021907006,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 64.39657956468047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 33,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.2371283141379,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.86653414034944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 59
    },
    {
      "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": 1673.6388165109624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.88434592732646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-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": 1672.1305254535307,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.59740424093167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1662.7933410041032,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.02021794771947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1662.6720777987493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.70473458705692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 94,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.9512272105483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 56.425112707893895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "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": 1644.3935809032257,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.72643086868543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 106,
      "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": 56,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.20016176997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.65215492250481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.606346995783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.095684875993925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.714783570323423,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "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": 78,
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.4348701230851,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.01588374094983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "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": 96,
      "draws": 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": 70,
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.9598470652513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.594117482982824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.04972212351036,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 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-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": 44,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.4100113362138,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.384304794269354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64
    },
    {
      "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": 1602.5266986191143,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.1027343192657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48,
      "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": 2,
      "distinct_rated_opponents": 24,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.3923852536077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.07459338705543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.97128781498596,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "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": 1599.0265614912312,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.00203493565957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 74,
      "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": 2,
      "distinct_rated_opponents": 37,
      "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": 58,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.8150260457114,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.82300342768883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.831799173767003,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-6-flash:dbac0d54294679dd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:45Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.777615993166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.59820019792202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.012467245703284,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 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": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6892957530818,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.31857245670056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "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": 52,
      "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": 1592.58297021455,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.19986121676889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 104,
      "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": 52,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-03T10:29:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.219415390376,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.16554962876789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64,
      "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": 2,
      "distinct_rated_opponents": 32,
      "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": 1601.2056239341523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.54275135535724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.52648327229861,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 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-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": 35,
      "max_score": null,
      "measured_at": "2026-08-03T14:14:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.1507673596157,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.52029893343254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 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-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": 48,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.875101313137,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.214571951063434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T00:59:23Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.0888414631513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.08920702046711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "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": 2,
      "distinct_rated_opponents": 17,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:06:16Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.477136059127,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.08738584494886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 59.14161899550908,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 1579.9273324684477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.778489355144025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.29557740277427,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meituan-longcat-2-0:ad7736e5bdc3d28f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:59:54Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.6106034519225,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Enabled (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.159506321412266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.84785372359809,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 60,
      "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": 4,
      "distinct_rated_opponents": 30,
      "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": 60,
      "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": "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.384263429241,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.10663380914288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.515204390048446,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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-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": 44,
      "max_score": null,
      "measured_at": "2026-08-03T12:11:33Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7911348935588,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.95611862982329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1549.9264735902525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.30683087113872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56,
      "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": 2,
      "distinct_rated_opponents": 28,
      "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": 32,
      "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 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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.497314720862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.28681973887564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.26463443331983,
      "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-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 38,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.2854909074172,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.21778129130201,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 112,
      "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": 48,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.9217609319278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.02325201056916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "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": 94,
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.6652469966723,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.02166558579286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.486412574268473,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 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-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": 55,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.2837822150532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.70493564691155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 2,
      "distinct_rated_opponents": 39,
      "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": 57,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.707459487237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.90001524707614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.644997148147095,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 63,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.5443530487862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.72757509137996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 2,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 61,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0164057321053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.394758803516936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.723103448694367,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 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": "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": 52,
      "max_score": null,
      "measured_at": "2026-08-04T23:21:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.3995628419666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.85922359902054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "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": "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.9564297708673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.75054191596875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9857641872218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.618288762349096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 80
    },
    {
      "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": 54,
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.9883204418932,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.6188762763087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.958864622419078,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 52,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.6944028280163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.83286645498502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 2,
      "distinct_rated_opponents": 27,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:27Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.235945481571,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.773354886116735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.966995223862348,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 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": "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": 52,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9159982859114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.54851301568021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 64,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.9069818743108,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.79792203718302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 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-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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:49Z",
      "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": 1490.8078638278364,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.629120841132384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 53,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9062628518725,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.21284375873298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.72324997517388,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 68,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0224962569089,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.32822843528254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:o3:416a436309f013a4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 89,
      "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": "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": 123,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:49Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.0897511504677,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.20081700407619,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.98079888322023,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.8352266808859,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.07016716141857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.518758273283815,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 56,
      "draws": 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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.2367408862915,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.69149287984802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 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": "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3098804014994,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.408119849833696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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": "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2800289578179,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.62067621907194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 50,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0951747410882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.474899556627776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.966995223862348,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.2181246632692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.82165124902767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 56,
      "draws": 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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.9492077155455,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.51172275800236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:20:21Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0141768671742,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.33051290926278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "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": 4,
      "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": "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": 114,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.4301689763815,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.77351511539399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.164515785801473,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.8157181355555,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.314784356383484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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": "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.2176833271508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.0464884077659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "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": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 97,
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.1880042694345,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.214929708588905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 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": "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.0311903903728,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.009668601208,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "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": 2,
      "distinct_rated_opponents": 13,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T03:10:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.6546307873011,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.50243701119809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.26384793916254,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "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": 4,
      "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": "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": 122,
      "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": "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5936547110098,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.83100441041674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.080489386472888,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "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": 105,
      "draws": 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": 139,
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.3985429518834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.736801434866358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 2,
      "distinct_rated_opponents": 29,
      "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": 71,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.4036140944768,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.25192540880105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.507220868368073,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1365.2585538585686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.241575056843985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.96298192699785,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 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-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": 64,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.5279664398565,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.935953546031328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "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": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 89,
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8203598823284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.320286766981738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.867341638060083,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:51:41Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.9093913458112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.878231343301803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 26,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T05:25:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.5292879263502,
      "reasoning_bracket": "balanced",
      "reasoning_level": "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.66347897180257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.70266341964107,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "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": 4,
      "distinct_rated_opponents": 36,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.107361683862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.580760401626307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.51543856721756,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "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": 2,
      "distinct_rated_opponents": 28,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.272383068994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.302124280326495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.406749398777613,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 2,
      "distinct_rated_opponents": 33,
      "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": 72,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.5974695891684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.41411822823543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.824399540348086,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "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": 74,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:34Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.8037388255002,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.515428670623326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 70,
      "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": 4,
      "distinct_rated_opponents": 35,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:54Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1298.0725132394223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.614276485732244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.00101022325288,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "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": "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": 63,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.3618154778578,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.886909831937842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.996324165557496,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 46,
      "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": 4,
      "distinct_rated_opponents": 22,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T03:18:11Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.3724729141295,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.932093277185512,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.40581686499769,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "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": 1239.8542944594315,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.8000252646134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1236.6737860033923,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.314483317000402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": 68,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1245.704202029921,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.44510307833982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "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": 1206.244527485814,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.548948613994082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 178,
      "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": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 126,
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1198.143112700935,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.631497595831043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.573428145379982,
      "unilateral_faults": 4,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "draws": 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": 57,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1199.66391873774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.498926473385124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 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-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": 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": "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": 1184.8550619458447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 12.488827301220297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 2,
      "distinct_rated_opponents": 34,
      "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": 1091.7576172341132,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 2.3222203559783994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.37850172271408,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "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": 1059.7162217483137,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 0.5457336893360095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82,
      "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": 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-5.4",
        "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1935.9305085166034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1924.0542264240664,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 99.17317608622864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1892.891192538813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 95.42130277416098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82,
      "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": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1880.0797890873182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 94.05837364506577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.949290834117,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 93.83172258846857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "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": 66,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:36Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1862.8922755189858,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 91.70201059215609,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 111
    },
    {
      "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": 1843.3512911845396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 90.25968655583348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 80,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T22:59:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.081054869981,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.7032381321606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "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": 46,
      "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": 1792.977450720159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.05033494665588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84,
      "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": 39,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1786.9238690390182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 84.20334702445369,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 46,
      "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": 1783.3077264160918,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 84.02163040431354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "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": 45,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.7289447776332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 83.06075814643916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 40,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.888067823131,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 81.11440057033718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 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-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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.344551427424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 78.97727049438612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 42,
      "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": 2,
      "distinct_rated_opponents": 21,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1743.6380722729027,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 77.64645353476814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 64,
      "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": 4,
      "distinct_rated_opponents": 32,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:42Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1721.3048744665289,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "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": "openrouter",
        "provider_setting_label": "High (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "High (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 74.49579059518622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.52149864255874,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 2,
      "distinct_rated_opponents": 31,
      "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": 1706.3705923810853,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 74.1617078908414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.779077868707382,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "draws": 8,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.2495360528883,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.48046758902608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.1398493340357,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 70.68540227201106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 68,
      "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": 34,
      "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": "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.2045242420968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.68324241888193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 2,
      "distinct_rated_opponents": 31,
      "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": 1656.371302041338,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.21005238359456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.461325131721317,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "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": 1642.2089240234834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.86134465387879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "draws": 8,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.1996547008405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.24458515523042,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 30,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.439897764506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.5532044937622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.51471483712608,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed: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": 48,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.9350142082228,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.09501277916272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 210,
      "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": 105,
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.6886921793475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 65.72313807060283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 42,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.5937026330773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 65.54813103397758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 144,
      "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": 72,
      "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": 62,
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.5598024695696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 64.32999385511812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 40,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.115508396417,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.54103500269817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 34,
      "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": "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": 28,
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.8776884828033,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.62712426295049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "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": 29,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0538051265532,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.619735110933746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 106,
      "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": 53,
      "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": 42,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.0883296357088,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.06281243846746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.7623852068155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.23827813661711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.61757338116737,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 41,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.301435818596,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.224644528934874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.951579906118113,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 46,
      "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": 4,
      "distinct_rated_opponents": 23,
      "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": "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:58Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.5740263790071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 60.72491770132335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.41404858347368,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "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": 34,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.774398115172,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 60.675097556373565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44
    },
    {
      "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": 64,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.0912104072377,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 60.02072384999008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:42Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.8531936911686,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.445585881637015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "distinct_rated_opponents": 24,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:14Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.000524633293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.81921687216023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.08892829743688,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 2,
      "distinct_rated_opponents": 33,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.1002332195922,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.49270207782266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.05007382550214,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 2,
      "distinct_rated_opponents": 27,
      "draws": 8,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.720666438107,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.38133319989706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.383827667425074,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "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": 2,
      "distinct_rated_opponents": 21,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:40Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.1505318997167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.264113485188496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.79847712741413,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "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": 83,
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.3957982687718,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.183064819125406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.807372224754609,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 194,
      "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": 95,
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.7080123574883,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.921126092380206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 41,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.497978964082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.85823075496087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "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": 2,
      "distinct_rated_opponents": 13,
      "draws": 3,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.1147152275953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.719235037247856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.405962904620324,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.4632087444165,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.40923463191768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 72,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.0993164354797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.69217513632242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "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": 102,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 103,
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2567073413627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.81464157035592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.2120790081366986,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "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": 40,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2036667060856,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.13788519283952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:416a436309f013a4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 59,
      "draws": 7,
      "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": "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": 95,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.2972836372262,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.99483797073365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.89539365739238,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 58,
      "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": 51,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.154060432485,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.76005671360996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 65,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-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": 80,
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.1115221856815,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.375926945379035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_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": 120,
      "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": 60,
      "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": 61,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0865376108627,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.2652285508529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 44,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8800041097018,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.87752410093403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "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": 4,
      "distinct_rated_opponents": 26,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T05:13:15Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7897534664867,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.7133517329692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.068051901535554,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed: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": 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": 34,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4590360383802,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.321870346065246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 49,
      "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": 51,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7393326842414,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.266797985099174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 56,
      "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": 61,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.5606086737382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.6628100593333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 48,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-03T13:57:32Z",
      "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": 1417.4757599964255,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.23874521686571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60,
      "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": 2,
      "distinct_rated_opponents": 30,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.073566639609,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.426727828824966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.29025629120688,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 25,
      "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": "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:51Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.121552122143,
      "reasoning_bracket": "balanced",
      "reasoning_level": "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.424054904650205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.381644683851405,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 71,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.594146627393,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.08045186567497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.259682442018587,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 60,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.6267806671017,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.140290158190794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "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": 61,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 1384.137730967665,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.11628633456594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58,
      "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": 4,
      "distinct_rated_opponents": 29,
      "draws": 19,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:31Z",
      "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": 151,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8525286946704,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.68827725343043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.69042571037485,
      "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: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": 1378.8243454602684,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.942819015465346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1373.38682774224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.63225251749573,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1370.0835377541052,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.23952442879587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 49,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": "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": 56,
      "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": 87,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.7788982716947,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.94026033234647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.63737751059915,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 53,
      "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": 56,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.1456650071532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.80306201224402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1365.4665711563578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.705796487312476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "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": 1354.325516280026,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.4033081726625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.629534578008435,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "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": 1353.3784605717633,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.13197671164298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.633827169132047,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meituan-longcat-2-0:ad7736e5bdc3d28f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:35:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.4736486683576,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Enabled (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.007594729040086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.964285714285715,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 1350.2598567148952,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.860401930611594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.926543555546573,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:cceee2fda7208875",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 18,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.8542682799737,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.04625714839305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.2356618633981,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "distinct_rated_opponents": 24,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.5567794486105,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.16163840382044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.00772618643724,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "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": 76,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.6101532628288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.937512179985525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 57,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.2737990682394,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.48264176849661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 24
    },
    {
      "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": 1301.6867097939717,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.46925549155916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": 60,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1312.5406298877297,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.00389460443945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "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": 1295.593141086351,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.82099690512065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 45,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": 64,
      "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": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.513648432589,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.215153717922618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.824774753010004,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "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": 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": "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": 67,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:25Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.0206728248031,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.92584138096761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.857940612168754,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "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": 2,
      "distinct_rated_opponents": 21,
      "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": 63,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.898542312292,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.65897798586819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "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": 1279.3223943837968,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.541429111812185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1291.4802446130302,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.414777820507236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1276.4806787457837,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.26055359128659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1270.3210113293824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.784727597962565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "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": 44,
      "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": 65,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.588396713997,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.534623279080066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 2,
      "distinct_rated_opponents": 35,
      "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": 1253.7861307495552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.078598419102768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.01928828118566,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "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": 1177.8349760515114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.56075363575773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 103,
      "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": 1170.0753284490197,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.463800160566905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 140,
      "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": 70,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 113,
      "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": "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": 1180.5673528891352,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.262080807158373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 25
    },
    {
      "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": 1036.920602437529,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 4.569710286459858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 78,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 2048.6955646228785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.5526124609985,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 92.05790847852163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1934.857523033671,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 89.10077480456111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 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": "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.5748924741924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.32857790093769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.763809051045354,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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-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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1835.2604164135125,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 79.18257070094032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:GB2-07: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": 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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:46Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1808.0596113105762,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 76.38776402098694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "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": 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-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": "2026-08-05T03:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1803.2582355928973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 75.86448374979243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 69
    },
    {
      "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": 1762.4042745072609,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.79611330973476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 92,
      "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": 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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1761.1968899835726,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.72102167529864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 44,
      "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": 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": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.0405753174614,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.71379024439247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "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": 47,
      "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": 1732.0611905000076,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.86330432028504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "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": 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": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1713.9112383774284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.9670189086873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1705.0967292013736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.08924139036272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 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": 1696.3443936235544,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.10196361472715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.22106228946894,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 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-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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.8017327798075,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.58738719657233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": "2026-08-05T00:35:22Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.940513626986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.3891044858804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 36,
      "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": 2,
      "distinct_rated_opponents": 18,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.4839434630712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.78676996714175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.90421938533743,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 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-5.4",
        "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.147005295843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 60.331355683982295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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: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": 1641.3171931289405,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.9101347289806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "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": 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",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:28:28Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.5757431946397,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.63713222006284,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1630.4735516007104,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.08648524326837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 92,
      "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": 46,
      "draws": 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": "2026-08-03T10:15:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.70258494576,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.024723737278265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:53Z",
      "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": 1633.041024252725,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.95884336983468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 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": "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1624.3448206991122,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.2984762422112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "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": 69,
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.5484097321898,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 56.37719386108883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 81
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 40,
      "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": 4,
      "distinct_rated_opponents": 20,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6202653307714,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.047608947568996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.41666726374335,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 47,
      "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": 52,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.3030320455705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.98808344707694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 51,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0678904088375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.26204637051112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:24:30Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.4714041645075,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.20659865554057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.037213613920954,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": 40,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.3036199131727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.012833138486045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "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": 35,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1603536781683,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.294481025847816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T15:10:28Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.9932384807714,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.77796349718378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.62217943844404,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meituan-longcat-2-0:ad7736e5bdc3d28f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.0957052938352,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Enabled (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.16968167475123,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.385605614968945,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 85,
      "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": "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.44883752229,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.107484759458345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.357735929582898,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "draws": 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": 36,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.93981257272,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.181270461651444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 50,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.1539016254237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.044380476224916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 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_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": 38,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.7177285588737,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.91951412041442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 203,
      "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": 96,
      "draws": 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": 106,
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.4789026376432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.644464757221996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.759599509820776,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.2161928372725,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.492651104691994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 2,
      "distinct_rated_opponents": 27,
      "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": 42,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.486896567064,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.4873271878866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.992031574433888,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 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-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": 45,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.1610657525957,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.41579682248144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 32,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.2260932564172,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.862871057100186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 54,
      "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": 51,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.1958341337388,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.231533682902075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48,
      "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": 4,
      "distinct_rated_opponents": 22,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.5031817176923,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.20301710581384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.13344768758128,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "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": 2,
      "distinct_rated_opponents": 28,
      "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": 43,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.1873552457232,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.61295183955477,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.395347377897878,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "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": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 79,
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.539579591432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.24855218994896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.409685569755814,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 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-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": 62,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.5171741625923,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.23625448361621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 54,
      "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": 50,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.5057890966405,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.768651176435434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 2,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 52,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.621615846795,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.72992644564387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.772182566181264,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 47,
      "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": 2,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T04:24:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 69,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.1110560655984,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "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": "openrouter",
        "provider_setting_label": "High (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "High (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.508716072525516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.46299533862032,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 2,
      "distinct_rated_opponents": 37,
      "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": 55,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.0117601373145,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.29733821571418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.242156042632452,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-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": 42,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.6131615979011,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.504203648777164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 104,
      "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": 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-4-5",
        "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:11Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.9594600967189,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.455587919211716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 2,
      "distinct_rated_opponents": 39,
      "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": 58,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.0811147075337,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.31918562226375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.40923597442238,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-05T04:24:34Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.7354986238543,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.28793172321607,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.36952453316905,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:cceee2fda7208875",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.5100071416261,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.1151076188509,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.25700210070024,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "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": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 99,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.7639380942178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.888503192541094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.773447205193634,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 2,
      "distinct_rated_opponents": 34,
      "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": 1471.5202267893505,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.70177239399337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.812711145915937,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "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": 74,
      "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": 86,
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.9013049678656,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.84966093971727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "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": 111,
      "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": "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.343706908703,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.71668659092171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.457164736907323,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "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": 58,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.8694948539608,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.59938350830355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "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": 4,
      "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-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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.9736603594838,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.48268724940904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.68183907783984,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "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": 1451.8589119440062,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.09138610591313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:416a436309f013a4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 93,
      "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": "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": 155,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.3384324946082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.03071689347571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.06107675388781,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "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": 1440.0116718921627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.64455151180685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66,
      "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": 2,
      "distinct_rated_opponents": 33,
      "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": 1450.0872590593376,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.53188452999624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.258608963549943,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "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": 112,
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8563076431074,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.013798787289424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.025404183609156,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 2,
      "distinct_rated_opponents": 33,
      "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": 55,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.5635626395624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.35594935305769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.91700367222747,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 68,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.18954362656,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.264518924471545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 2,
      "distinct_rated_opponents": 29,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:11Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8399822560605,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.98262964892139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.698553251899696,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "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": 57,
      "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": 1401.2822756940366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.2955991645047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1406.6667442109426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.22574841026145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66,
      "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": 2,
      "distinct_rated_opponents": 33,
      "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": 1408.3766454374631,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.094131414739394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.824399540348086,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.472304078443,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.25781838363284,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.941634169259466,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 61,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.9371892145195,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.24914236422956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.381644683851405,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "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": 1377.7199812397787,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.70010205201074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48,
      "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": 2,
      "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": "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.7784399022385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.479903919492436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.08892829743688,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "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": 1364.5064243167951,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.460482495895945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53,
      "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": 2,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 64,
      "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": 99,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.418971602498,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.32531783828087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.736938746462222,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 63,
      "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": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.7720405010791,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.686045371959437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.10955497609672,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 65,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.9276344632324,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.48344557638085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.597143087872503,
      "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": 1302.1104543187066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.064607743882533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1299.2820176175837,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.63023441070387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64,
      "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": 2,
      "distinct_rated_opponents": 32,
      "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": 1307.8916232961728,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.202311210174184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "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": 1288.3055324602838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.48890361547792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48,
      "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": 2,
      "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": "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.7021143336742,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.789612194123116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.48369970321018,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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": 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": "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.5590178307139,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.97030061327731,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 22,
      "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": 54,
      "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": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.0939707885482,
      "reasoning_bracket": "balanced",
      "reasoning_level": "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.993586011581286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.51779962499649,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 73,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.3442248132515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.504897803108722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.714783570323423,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "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": 1216.326014794011,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.320948925619717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 68,
      "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": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1196.149393725581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.786907510390217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1179.1916405345034,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.294011760456632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1172.2216045615141,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 12.928888178071984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 1165.7290719890677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 12.422397885640807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1144.1874341325886,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 10.185410895530666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1131.5762374150424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 8.83134021951195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 92,
      "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": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 80,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1052.903259206907,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 1.18683615794815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 1045.6951836273022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 100,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 2047.0897119000806,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "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": 101,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1902.1030786263232,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 82.83097754139442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 174
    },
    {
      "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": 1882.0961693922998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 80.48164573606203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 1814.5336004592846,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.22544650832927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 17,
      "max_score": null,
      "measured_at": "2026-08-04T21:52:45Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.2666943887314,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.00313139343699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 46,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1783.5389156654253,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.79504598485697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:31Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1801.6806806916547,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.5646741796879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.62217943844404,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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-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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.1633732381583,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.15920342920347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1778.443049602078,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.83663626822397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 170,
      "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": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.0794210582203,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.46916572650451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:16:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.8005525842925,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.02362320555288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 2,
      "distinct_rated_opponents": 24,
      "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": "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": "2026-08-05T03:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.3276397387067,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.94474034970983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.00772618643724,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.4200337972638,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.52956277651462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 54,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.2256601683764,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.27779754414018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-04T23:19:16Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.6482757361791,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.895170182688986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.84785372359809,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "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": "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": 48,
      "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": "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.752162859162,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.60650013104014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.43756316443626,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "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": 25,
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1668.6588000800791,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.40256274594081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 2,
      "distinct_rated_opponents": 30,
      "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": 1674.6742605175516,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.725778913783415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.291258434495777,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "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": "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.1650048305432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.14226731360425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 17,
      "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": "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.1866708150255,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.848011910482846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 46,
      "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": 32,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.127256233949,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.731858204888034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 51
    },
    {
      "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": 94,
      "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": 1610.5029346193264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.084198694140696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 56,
      "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": 1605.807541988619,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.93181649730258,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:44Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.0681246470708,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "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": "openrouter",
        "provider_setting_label": "High (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "High (historical request variant 2)",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.684012366397255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.22404724625551,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 47,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.560257343934,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.28913787090833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.1255280580322,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.24817449486797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.473660794592899,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "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": 1539.1028287524625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.5657581912891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.6791586355407,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.2429231453361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.221225597086458,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "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": 1525.8670668329498,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.37160182164898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1523.101241228136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.77081834649088,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 54,
      "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": 1485.5625871021477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.5924272304032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.0922204178614,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.060420135068554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.411612305726376,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 63,
      "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": "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": 1466.4297670164335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.624425793989726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:416a436309f013a4",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 78,
      "draws": 83,
      "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": "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:23Z",
      "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": 205,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.627888866674,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.512771329112983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.770121842860966,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.2219261759235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.292543079332418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": 43,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.7095025143608,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.551395750129856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.674278837447822,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "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": "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.841570816661,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.38959639303247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 12
    },
    {
      "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": 59,
      "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": 1444.8116248114163,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.95538217774586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 76,
      "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": "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.6728163873909,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.55499914859909,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.809420939187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.28574181894595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 130,
      "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": 65,
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.5502098452275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.179696020170926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_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": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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-5.5",
        "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4705060316537,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.041252381178502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.356567823582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.91580429175553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 57,
      "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": 1436.6611574632266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.91395572652641,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8580197603374,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.878320723885658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "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": "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4194727656443,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.84632818688169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.4850403755702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.612132302735073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-04T06:58:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4052725343836,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.577174727119328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": 1447.77340818449,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.4196347480646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.976534673506283,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 71,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:25:51Z",
      "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": 71,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.2338469609456,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.407921076039756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.175565098878963,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 94,
      "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": "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0354741384447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.126778881865853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.4023399340574,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.014259316222454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 262,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 122,
      "draws": 262,
      "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": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.9452372916912,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.757380406088267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_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": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8137881433222,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.641010675069595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 83,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.2683033126514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.602617521323882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.5465939205094,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.3984628011689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 189,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3405534391286,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.29547231816128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.2229879671406,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.27689482403025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 82,
      "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": "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.9709089457906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.170508876258452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.5039592688865,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.160395258498756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:36:46Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.7671715437525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.132200293916647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.79047988958712,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 44,
      "draws": 139,
      "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": 23,
      "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": "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.586080274788,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.037611680027343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.561240097148016,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 140,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.6670918396599,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.99912090816997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.818262520573185,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 116,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 23,
      "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": "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.7827706058372,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.963666797879824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.836607386351783,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.7720758672476,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.918992285254213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.044184037997496,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 37,
      "draws": 134,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:50:28Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.316209227975,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.899207454188396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.68291638854062,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4684130812043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.882984936169017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.044184037997496,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.9759189337483,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.83019830376679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 41,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 27,
      "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": "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3383987718696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.440155577244205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.54983807626827,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": 1432.9907321597134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.40155383767231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.772182566181264,
      "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:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.188024322118,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.366216398962596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 50,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.6268161240855,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.257408425790306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 50,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:40Z",
      "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": 1431.2672956941567,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.841215591728457,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.524801725696737,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 72,
      "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": "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.6697828592557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.606530359301495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.422225981586,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.5968014699668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:cceee2fda7208875",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:50:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.7879644482614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.102373476112174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.964285714285715,
      "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:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.1981627791558,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.94602226083568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.469355363088,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.61062430589122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 62,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.6136814138022,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.50219767108876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.0733020497882,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 46,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:32Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.880964666142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.28639305487321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.22404724625551,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.0939080345697,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.090076092259295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.059739949501434,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 2,
      "distinct_rated_opponents": 26,
      "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": "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": 27,
      "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": "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.1744868927296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.034961332646205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.491466493865985,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": "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": 16,
      "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": "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.745642412368,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.033193461986272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.22404724625551,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.32775976306,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.92692217247133,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.32197342861184,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.128132796408,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.65639270005456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.674278837447822,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 54,
      "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": "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.3551553183834,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.462701167505323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.0097337160018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.377364901924253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.21770585958794,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:dbac0d54294679dd",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "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": 26,
      "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": "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.5580809943738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.053219546938315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.07018134211407,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "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": 78,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.6272805817675,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.369345026768944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.865877260366762,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 50,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.8902558829477,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.34202322749009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 73,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.5044432580917,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.841275546599956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.779077868707382,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 21,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.2923757001072,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.20229853735902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5064376721202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.05599677831604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.059739949501434,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:ad7736e5bdc3d28f",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 41,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.0654464521704,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Enabled (historical request variant 1)",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.843454373359577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.44099895136409,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.149327600217,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.856581427150502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.7791209706893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.591710349239374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.003433595313624,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "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": "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.1602691915714,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 12.01937572804176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.054940481631803,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": 69,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.3292533208191,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 5.696416759421026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.170873961698575,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 41,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-5:f42601f844754f74",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:35:16Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 43.10391328842407,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.0268077344185,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 72.16867361924449,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:e2f72ed41374a73b",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 28
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 3.2933475,
        "mean": 1.0782631249999999,
        "median": 0.5065824999999999,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 28
        },
        "run_count": 24,
        "token_priced_attempt_count": 28,
        "total": 25.878315
      },
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T06:55:12Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 22.571342246704436,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.7525502117269,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 56.905591925345966,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:2c7771c40a0c79dd",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 12.915325,
        "mean": 3.549568958333333,
        "median": 0.4352825,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 27
        },
        "run_count": 26,
        "token_priced_attempt_count": 27,
        "total": 85.663355
      },
      "codegen_evaluated_cells": 26,
      "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-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:17:02Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 20.34202322749009,
      "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": 1623.0890353562586,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 55.341616697809656,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-4-8:164e2eeded186d37",
      "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-2026-07-30": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:49:27Z",
      "losses": null,
      "max_score": 85.7032381321606,
      "measured_at": null,
      "min_score": 20.525841154304743,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.6049565689482,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 51.0838604570741,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:b8f6c70d3173c941",
      "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-2026-07-30": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 26.566349999999996
      },
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 94.05837364506577,
      "measured_at": null,
      "min_score": 15.142060466906322,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.8079457174965,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 50.568334747025915,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:eac4d255581f5932",
      "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-2026-07-30": 34
        },
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 1.6998543999999995
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 40,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:42:30Z",
      "losses": null,
      "max_score": 80.48164573606203,
      "measured_at": null,
      "min_score": 6.748867164434723,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.0053195929977,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 46.63852829188297,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:3e7c051458a7cbef",
      "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-2026-07-30": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 78.97727049438612,
      "measured_at": null,
      "min_score": 24.606530359301495,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.1953002017776,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 45.25247559054204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 38,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-6-flash:c02c4e37bd6ab352",
      "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": 12.701101349999997
      },
      "codegen_evaluated_cells": 44,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 70,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 30,
      "first_pass_rate": 0.6818181818181818,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "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": null,
      "max_score": 91.70201059215609,
      "measured_at": null,
      "min_score": 18.71384108753165,
      "model_code_failure_rate": 0.13636363636363635,
      "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": 1576.0083626210653,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.18181818181818182,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 43.3340106215883,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:a93d7b20a8cd643a",
      "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-2026-07-30": 25
        },
        "run_count": 40,
        "token_priced_attempt_count": 41,
        "total": 11.203785
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 32,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:15Z",
      "losses": null,
      "max_score": 69.00313139343699,
      "measured_at": null,
      "min_score": 7.670088947709001,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.3647423401894,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.03361346295353,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-k3:7e275ce6898630a0",
      "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-2026-07-30": 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": 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": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": [],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:02Z",
      "losses": null,
      "max_score": 68.5646741796879,
      "measured_at": null,
      "min_score": 16.21094587734794,
      "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": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.755969341263,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.72540519959575,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:6e5fee7bd6a04cc5",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 28
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 4.987857,
        "mean": 1.074231,
        "median": 0.038529,
        "min": 0.016152,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 28
        },
        "run_count": 26,
        "token_priced_attempt_count": 28,
        "total": 29.297331
      },
      "codegen_evaluated_cells": 26,
      "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-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:41:40Z",
      "losses": null,
      "max_score": 81.11440057033718,
      "measured_at": null,
      "min_score": 0.5457336893360095,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.1058449905402,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.73520029108536,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:51c4a57bfa7f8191",
      "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": 70,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T06:55:18Z",
      "losses": null,
      "max_score": 60.72491770132335,
      "measured_at": null,
      "min_score": 18.932093277185512,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.9140269657628,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.069940185676966,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:0547893a49940f13",
      "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": 0.10342042200000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:11:31Z",
      "losses": null,
      "max_score": 66.5532044937622,
      "measured_at": null,
      "min_score": 10.87785451326086,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.7858717059107,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.098738934536954,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:claude-fable-5:e25aa4a60eafd473",
      "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-2026-07-30": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 47.83931957227835,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 75.53520861590758,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:fa85c3da121cf5b2",
      "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-2026-07-30": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T04:10:10Z",
      "losses": null,
      "max_score": 47.75501155028078,
      "measured_at": null,
      "min_score": 47.75501155028078,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.75501155028078,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:claude-sonnet-5:bda869958eedd23a",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 10,
        "cost_basis_counts": {
          "estimated": 1,
          "local_list_price_estimate": 12,
          "provider_dashboard_reconciled": 1
        },
        "evidence_basis": "Combined: Provider-reported + Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.469661,
        "mean": 0.11842290000000003,
        "median": 0.074902,
        "min": 0.05673,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-30": 11
        },
        "recorded_attempt_count": 2,
        "run_count": 11,
        "token_priced_attempt_count": 12,
        "total": 1.6538899999999999
      },
      "codegen_evaluated_cells": 11,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 9,
      "first_pass_rate": 0.8181818181818182,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-03"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:02:41Z",
      "losses": null,
      "max_score": 52.82357979001043,
      "measured_at": null,
      "min_score": 26.602617521323882,
      "model_code_failure_rate": 0.09090909090909091,
      "model_code_failures": 1,
      "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": "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-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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.09090909090909091,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 45.73992115934501,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:d06731d4b4c0d390",
      "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": 20,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 93.17614952930187,
      "measured_at": null,
      "min_score": 13.591710349239374,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 45.60063533806962,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-5-2:19198473790d4b05",
      "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": 1.0676026350599999
      },
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T04:45:51Z",
      "losses": null,
      "max_score": 69.68324241888193,
      "measured_at": null,
      "min_score": 20.60128829346809,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.5160686444135,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 41.04706919432293,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:740077efda94b582",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 71.11107962938964,
      "measured_at": null,
      "min_score": 23.61062430589122,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.22586600111486,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-5:8fed194f257c1858",
      "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-2026-07-30": 19
        },
        "run_count": 24,
        "token_priced_attempt_count": 31,
        "total": 4.45591875
      },
      "codegen_evaluated_cells": 16,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 68.24458515523042,
      "measured_at": null,
      "min_score": 16.47955768015164,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.215344908162436,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:626f807d89d29d00",
      "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": 0.9112224999999998
      },
      "codegen_evaluated_cells": 16,
      "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": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 66.08924139036272,
      "measured_at": null,
      "min_score": 20.826508924484237,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.93936360364965,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:a57de75253bd5178",
      "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": 1.2846227784
      },
      "codegen_evaluated_cells": 15,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": null,
      "max_score": 69.21005238359456,
      "measured_at": null,
      "min_score": 19.841275546599956,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.8438557392716,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:f5db0c1d0a868367",
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.4575640000000001
      },
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 60.675097556373565,
      "measured_at": null,
      "min_score": 12.488827301220297,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.374773927607926,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:c03104ecd4a13abe",
      "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": 1.283003154
      },
      "codegen_evaluated_cells": 8,
      "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": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 53.725778913783415,
      "measured_at": null,
      "min_score": 22.092590644226938,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.29498316942586,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:94f2248333cf147d",
      "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-2026-07-30": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 65.72313807060283,
      "measured_at": null,
      "min_score": 15.418465089790947,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.78761643752565,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:fa0cf056c5665489",
      "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-2026-07-30": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 62.06281243846746,
      "measured_at": null,
      "min_score": 10.185410895530666,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.61151584414168,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:f60a5042bde2be06",
      "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": 0.08653749999999999,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-07-30": 56
        },
        "recorded_attempt_count": 40,
        "run_count": 48,
        "token_priced_attempt_count": 29,
        "total": 4.201686
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 52,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:17:46Z",
      "losses": null,
      "max_score": 65.54813103397758,
      "measured_at": null,
      "min_score": 24.102373476112174,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.0966129410888,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 35.19701876585024,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:c77180cf8fb08edd",
      "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": 0.48528460000000007
      },
      "codegen_evaluated_cells": 8,
      "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": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 51.82300342768883,
      "measured_at": null,
      "min_score": 23.203770649071114,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 34.04254490373653,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:3efce85b482761c7",
      "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": 0.5164659199999999
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 18,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 74.1617078908414,
      "measured_at": null,
      "min_score": 8.83134021951195,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.59000467698186,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:b1da6d00e44bbdf5",
      "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": 34,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:35:16Z",
      "losses": null,
      "max_score": 52.594117482982824,
      "measured_at": null,
      "min_score": 18.97110273604848,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.93510151640261,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:3c5fef0475ec7b6e",
      "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": 0.041725612999999995
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 20,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 71.41435556334146,
      "measured_at": null,
      "min_score": 9.407687981142418,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.1411717990917,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:6ff688fbb800bfea",
      "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": 0.0625307
      },
      "codegen_evaluated_cells": 14,
      "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/gemma-4-31b-it",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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"
      ],
      "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": 45.90001524707614,
      "measured_at": null,
      "min_score": 14.548948613994082,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.898264549296297,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:9efcd5e1b19ad9d9",
      "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": 0.14908945063999998
      },
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 69.71379024439247,
      "measured_at": null,
      "min_score": 9.943666245746922,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.4944823062096,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.823810468802048,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-v2-5:5ca3d328ffb17b98",
      "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": 52,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 62.62712426295049,
      "measured_at": null,
      "min_score": 18.9315557741441,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.0611683132424,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.139545504730307,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-m3:306f6bca3b4c3882",
      "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": 0.78755832
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 20,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 51.404796674852406,
      "measured_at": null,
      "min_score": 2.3222203559783994,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.098700766251334,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:meituan-longcat-2-0:4f1d1a6fc03112d2",
      "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": 27,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 38,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 15,
      "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": [
        "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": "2026-08-05T05:41:26Z",
      "losses": null,
      "max_score": 51.81464157035592,
      "measured_at": null,
      "min_score": 13.631497595831043,
      "model_code_failure_rate": 0.2222222222222222,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.28499351265294,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:fff0903df45f4b1d",
      "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": 1.00006698
      },
      "codegen_evaluated_cells": 24,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:41:59Z",
      "losses": null,
      "max_score": 61.23827813661711,
      "measured_at": null,
      "min_score": 15.139582069381618,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.1093510899077,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.980909796261443,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:a8eec1465fa7e4b4",
      "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": 1.2116408499999998
      },
      "codegen_evaluated_cells": 34,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 30,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 66.09501277916272,
      "measured_at": null,
      "min_score": 12.422397885640807,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.052506892298,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.741343599571106,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:ac46b2b3feb2053c",
      "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": 6.000973940000001
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 36,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:41:54Z",
      "losses": null,
      "max_score": 63.27779754414018,
      "measured_at": null,
      "min_score": 14.786907510390217,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.478513894234,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 26.990199775004637,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:0641171d97b75bfa",
      "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": 3.4057992500000007
      },
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 59.024723737278265,
      "measured_at": null,
      "min_score": 5.696416759421026,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.86401053026094,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:b5a9710ceba35181",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 43.6188762763087,
      "measured_at": null,
      "min_score": 19.266038248032807,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 23.88292168813816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:ebf74d4ed7b0916f",
      "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": 2.2589025
      },
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 44.576050565533166,
      "measured_at": null,
      "min_score": 14.583182450662427,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 23.64973471887243,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:4a5b21798b8d9375",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 40.71668659092171,
      "measured_at": null,
      "min_score": 14.944434766576471,
      "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": null,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 22.899725766295553,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:caa30ce7ab70c2c5",
      "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": 0.348093
      },
      "codegen_evaluated_cells": 24,
      "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": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 49.375926945379035,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.6771787049456,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 22.267310132093026,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 74.90272134044969,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 176,
      "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": 233,
      "max_score": 95.74255598925224,
      "measured_at": null,
      "min_score": 44.983185125573506,
      "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": 1314,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.1800960050934,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 72.44353093299611,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 905
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0371999999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.6964642118633,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 68,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 147,
      "max_score": 84.02163040431354,
      "measured_at": null,
      "min_score": 47.83931957227835,
      "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": 620,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.031207905637,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 66.44103633431087,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 405
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "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": 0.6689649999999999,
        "mean": 0.46799875,
        "median": 0.4352825,
        "min": 0.36661499999999997,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 4.1199200000000005
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 58.665774525975536,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 154,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 180,
      "max_score": 85.05033494665588,
      "measured_at": null,
      "min_score": 39.33968507396859,
      "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": 714,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.8401666025802,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 0.1111111111111111,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 56.96350162639645,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash:9815232c2420f539",
      "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": 2.7900240000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.54328630060818,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 187,
      "max_score": 93.17614952930187,
      "measured_at": null,
      "min_score": 19.20229853735902,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.4485540370158,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 53.54328630060818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 311
    },
    {
      "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-2026-07-30": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.5087456
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.49184542328232,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 192,
      "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": 247,
      "max_score": 80.48164573606203,
      "measured_at": null,
      "min_score": 30.44728628591251,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 834,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.5843011865275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 53.49184542328232,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 395
    },
    {
      "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": 4.169687700000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 53.090232750620466,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 306,
      "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": "2026-08-05T06:55:12Z",
      "losses": 232,
      "max_score": 91.70201059215609,
      "measured_at": null,
      "min_score": 21.969050080927598,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1054,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.216065675475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 51.347185385006284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 516
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.5428549999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.615805651408955,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 253,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 222,
      "max_score": 68.86330432028504,
      "measured_at": null,
      "min_score": 31.14381674077765,
      "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": 774,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.2727402600594,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 50.615805651408955,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "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": 0.712055,
        "mean": 0.49864374999999994,
        "median": 0.5065824999999999,
        "min": 0.29423750000000004,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.98915
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.969059392457204,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 235,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 200,
      "max_score": 95.42130277416098,
      "measured_at": null,
      "min_score": 23.285331416066995,
      "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": 740,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.079898179778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.969059392457204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 305
    },
    {
      "admitted_plugins": 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-2026-07-30": 8
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 3.34216
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.72055502526362,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:57:11Z",
      "losses": 223,
      "max_score": 69.00313139343699,
      "measured_at": null,
      "min_score": 28.065418891234213,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 713,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.7871186649982,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 45.72055502526362,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 295
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 2.0151682500000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.59159045145555,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 250,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 247,
      "max_score": 62.06281243846746,
      "measured_at": null,
      "min_score": 25.554134372396923,
      "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": 805,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.0451461188636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 44.59159045145555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 308
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.39147302621685,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 297,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 203,
      "max_score": 83.06075814643916,
      "measured_at": null,
      "min_score": 20.525841154304743,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 758,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.4694399543234,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 43.39147302621685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 258
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "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",
        "failed_cell_count": 1,
        "max": 0.046574000000000004,
        "mean": 0.036155625000000004,
        "median": 0.035338,
        "min": 0.025803,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 0.31504800000000005
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 44.28791315320453,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 295,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 229,
      "max_score": 70.68540227201106,
      "measured_at": null,
      "min_score": 23.068325697614167,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 770,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.0247354322025,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 43.00283484393868,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 246
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:o3:f8a6e076cfc86cf1",
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.783799081191745,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 157,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 222,
      "max_score": 65.54813103397758,
      "measured_at": null,
      "min_score": 26.534569513484524,
      "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": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.866290235885,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.60662589311128,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.3395199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.6213249858686,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 287,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 250,
      "max_score": 54.85823075496087,
      "measured_at": null,
      "min_score": 26.523304025075756,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 784,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.672146949503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.6213249858686,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-plus:c53556cb68ddc5f3",
      "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": 43.52384843515179,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 198,
      "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": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 216,
      "max_score": 74.1617078908414,
      "measured_at": null,
      "min_score": 23.34842170383965,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.0488029127562,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.503504840575566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:z-ai-glm-5-2:ad9fb0aed35ae9e2",
      "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": 0.527165994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.36964566822354,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 225,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 160,
      "max_score": 69.68324241888193,
      "measured_at": null,
      "min_score": 22.919618819874938,
      "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": 562,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.9558617679425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.36964566822354,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "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": 0.132112,
        "mean": 0.0780535,
        "median": 0.06797,
        "min": 0.05673,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.624428
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.52323884508071,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 237,
      "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-sonnet-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 212,
      "max_score": 52.82357979001043,
      "measured_at": null,
      "min_score": 26.602617521323882,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 724,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.0733475614757,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.15995659275643,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.9368552071157,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 173,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 248,
      "max_score": 63.54103500269817,
      "measured_at": null,
      "min_score": 21.462701167505323,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8592472486805,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.625656769040205,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 217
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-nano:5c7ad4cb58558f0e",
      "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-2026-07-30": 25
        },
        "run_count": 16,
        "token_priced_attempt_count": 25,
        "total": 0.3954491500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 40.73000972203921,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 221,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 492,
      "max_score": 65.72313807060283,
      "measured_at": null,
      "min_score": 15.418465089790947,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1158,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.9488362584032,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.903544958605444,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 445
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:ad9b5d76213eb171",
      "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": 1.0777302952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.3417006630155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 125,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 221,
      "max_score": 69.21005238359456,
      "measured_at": null,
      "min_score": 19.841275546599956,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 530,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.9071743566915,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.54218266144462,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "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": 0.7288237499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.59132435668447,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 263,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 244,
      "max_score": 63.10196361472715,
      "measured_at": null,
      "min_score": 20.826508924484237,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 730,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.7336760614942,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.324302104748774,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k2-7-code:87a92cb1b6d3a644",
      "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": 1.283003154
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.076067521730096,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 183,
      "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": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 221,
      "max_score": 53.725778913783415,
      "measured_at": null,
      "min_score": 22.092590644226938,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 644,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.9528124625956,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.29498316942586,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 240
    },
    {
      "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-2026-07-30": 16
        },
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 2.3233296
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.05266115739552,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 172,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-05T06:56:50Z",
      "losses": 182,
      "max_score": 58.49270207782266,
      "measured_at": null,
      "min_score": 16.21094587734794,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.3521597522176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.05266115739552,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "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": 0.48528460000000007
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.04254490373653,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 315,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 290,
      "max_score": 51.82300342768883,
      "measured_at": null,
      "min_score": 23.203770649071114,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 826,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3195565883263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 34.04254490373653,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 221
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemma-4-31b-it:e2ccce3c75f0de36",
      "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": 37.22399240106636,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 74,
      "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": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": [],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:57:18Z",
      "losses": 194,
      "max_score": 45.90001524707614,
      "measured_at": null,
      "min_score": 28.508028292488625,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 436,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.3867339750273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.364092867730605,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "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": 0.01972526
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.330776405133705,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 312,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 238,
      "max_score": 42.11628633456594,
      "measured_at": null,
      "min_score": 25.98156528887542,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 689,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.521159281039,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.236467358124216,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:f51e041235d08cd6",
      "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": 35.535482548305495,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 182,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 66.09501277916272,
      "measured_at": null,
      "min_score": 12.422397885640807,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.9454948946297,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.679204262663337,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "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": 0.050973330659999996
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.58701354365491,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 360,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 421,
      "max_score": 43.00749050094252,
      "measured_at": null,
      "min_score": 21.190773152388033,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.4664548740934,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.549955352489913,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:cohere-north-mini-code:1aa694a2c1eb6ac2",
      "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": 30.62503365364087,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 186,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 261,
      "max_score": 43.6188762763087,
      "measured_at": null,
      "min_score": 20.369345026768944,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 632,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2196909932397,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.49980512824352,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "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": 0.48618750699999996
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 30.700755822837117,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 555,
      "eligibility_flag": true,
      "entry_count": 30,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 586,
      "max_score": 41.85354162714708,
      "measured_at": null,
      "min_score": 22.527432167882964,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1508,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.7316568571812,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 27.741264473852226,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 367
    },
    {
      "admitted_plugins": 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": 0.04917796000000001
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 28.794662059114653,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 366,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_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": "2026-08-05T05:35:16Z",
      "losses": 298,
      "max_score": 41.34256667887432,
      "measured_at": null,
      "min_score": 18.97110273604848,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 838,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.0072427940133,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 27.109914524444687,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-1-flash-lite:71cb71219c9b05f8",
      "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": 28.950627058556446,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 160,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 323,
      "max_score": 49.375926945379035,
      "measured_at": null,
      "min_score": 1.18683615794815,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 642,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.0438279595462,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 26.94159421474535,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "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": 0.6081093000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.596471622289776,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 378,
      "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": "2026-08-05T06:55:18Z",
      "losses": 411,
      "max_score": 45.4707813752063,
      "measured_at": null,
      "min_score": 19.262080807158373,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 987,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.1766818118472,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 26.690430064939164,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "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": 11,
      "conditional_success_score": 28.665869954402904,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 183,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 7,
      "first_pass_rate": 0.6363636363636364,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:36:51Z",
      "losses": 374,
      "max_score": 40.71582481684514,
      "measured_at": null,
      "min_score": 13.687976243904558,
      "model_code_failure_rate": 0.36363636363636365,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.6363636363636364,
      "provider": "Other",
      "provider_key": "other",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 800,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3339871241076,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 25.60303589173286,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 243
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "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": 25.77665339720033,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 240,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 345,
      "max_score": 46.29733821571418,
      "measured_at": null,
      "min_score": 2.3222203559783994,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.3301171841536,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.930359729410473,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 147
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:nex-agi-nex-n2-pro:5745a767d889956e",
      "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": 0.8197712500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.379395262676457,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 56,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 302,
      "max_score": 39.53188452999624,
      "measured_at": null,
      "min_score": 5.696416759421026,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.2670110256822,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 21.676688312409,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:stepfun-step-3-7-flash:61eef7ea1025a0f2",
      "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": 34.73179707606592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 149,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 160,
      "max_score": 41.79792203718302,
      "measured_at": null,
      "min_score": 26.292540253374842,
      "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": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6478697226069,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.205843656583273,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1.25526928
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.222332345871024,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 111,
      "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": "2026-08-05T05:29:13Z",
      "losses": 193,
      "max_score": 54.946552450271184,
      "measured_at": null,
      "min_score": 14.786907510390217,
      "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": 403,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.9727414911788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.432795454223083,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:inclusionai-ling-3-0-flash:d605eeb997ce6e73",
      "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": 26.689974102730307,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 132,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T05:35:50Z",
      "losses": 237,
      "max_score": 40.71668659092171,
      "measured_at": null,
      "min_score": 14.944434766576471,
      "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": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.052850804214,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 21.22575515545204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash:9815232c2420f539",
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:21Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1939.5874331556233,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 93.17614952930187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 75
    },
    {
      "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": 1799.055667309865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 78.50521178364832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T18:12:02Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1753.8905307528914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 73.22615883803878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 2,
      "wins": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.1942513938784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.5069715162629,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.730117399782776,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "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": 101,
      "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": 59,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.7127113138886,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.6194323591836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.975142627637888,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.0514577525005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.38623768514597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 2,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:10:46Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.1296139952278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 65.83747645882278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.1747525619378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.92984534569066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.6640036153567,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.59904938707476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.375137598157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.9941304808233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.2596975548165,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.415585713195995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 2,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:49:55Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.2086367687052,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.82357979001043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:f51e041235d08cd6",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.958621253768,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.990872009700986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-plus:c53556cb68ddc5f3",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:57:34Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.3703249093664,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.751145429420006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.48795150977726,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:29:40Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.6320452094085,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.06768139295753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:o3:f8a6e076cfc86cf1",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1494.2465984289327,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.6739398929183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:15Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.5961376388414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.4707813752063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1492.718192054946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.419750227325316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1501.4383086612108,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.92433554994799,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.21328729190924,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "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:71cb71219c9b05f8",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1468.2228066206737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.00333801213897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:87a92cb1b6d3a644",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1482.9632959237965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.8706174363605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.014839042432094,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "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:ad9fb0aed35ae9e2",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1469.1718670852033,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.524252957277774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "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": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:50Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.986338566357,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.10161283911572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 56.49112594673751,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1456.6726793206537,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.54726967322666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "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": "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": 28,
      "max_score": null,
      "measured_at": "2026-08-05T03:44:26Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.3773249800106,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.34256667887432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 45.81147465969834,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "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",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:29:13Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8495385633466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.916500267983515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 56,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1401.8023272025948,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.19298039167491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.52923410979691,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 80,
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.8120697560494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.05771191946257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.000430913942129,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1327.0032979772882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.9976913296341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.38386256637516,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "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:d605eeb997ce6e73",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.2462229301345,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.921401697168093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 47.5751600509567,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:11:21Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.3826997250194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.676297098775773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1303.4905060606818,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.261465808297835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.829266196477747,
      "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:5c7ad4cb58558f0e",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1213.8022511283734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.418465089790947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 30,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.47443747152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.88223492302193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 2,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "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": 72,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 15,
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.5328918965038,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.73552101088833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "capped_draws": 0,
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:42:13Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2391207094831,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.239355196944736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.4346988559294,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.54797454033727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 48,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.1232344259092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.44728628591251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-5-flash:9815232c2420f539",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3389302620424,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.285703310875242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 60,
      "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": 30,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T01:19:10Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.262611968492,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.065418891234213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 71,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.86953058894,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.753406537020762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.6607459565766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.523304025075756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:stepfun-step-3-7-flash:61eef7ea1025a0f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.647195989816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.292540253374842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.281346131285,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.98156528887542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-nano:5c7ad4cb58558f0e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 75,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.129902029356,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.578831533804646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1478.9493057309376,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.554134372396923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "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": 18,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 0,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.8163977249776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.741559061870756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-plus:c53556cb68ddc5f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1489.1136087685727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.34842170383965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.47940711208657,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4974252789027,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.285331416066995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1485.6883786648543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.203770649071114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.992031574433888,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.5711246807089,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.068325697614167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:z-ai-glm-5-2:ad9fb0aed35ae9e2",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.841977949159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.919618819874938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 71,
      "draws": 220,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.265940417252,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.527432167882964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.1772120160256,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:87a92cb1b6d3a644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "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": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:15:10Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.889844365115,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.092590644226938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.156172217111,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.969050080927598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:f51e041235d08cd6",
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2953460829026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.883388248077022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 66,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 19,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.7374764232438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.190773152388033,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.355146918744417,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "draws": 82,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.8304846432588,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.826508924484237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.97128781498596,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1459.9363913520322,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.525841154304743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 34,
      "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": 4,
      "distinct_rated_opponents": 16,
      "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": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.2086713176134,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.97110273604848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 58.88055773359793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 8,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:36Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2765108129372,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.40784673510266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 63.30774080334622,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "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": 2,
      "distinct_rated_opponents": 12,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.647858481688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.21094587734794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 78.125,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "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:d605eeb997ce6e73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "draws": 44,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T01:19:37Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.9368942846404,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.944434766576471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 51.89801750319316,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1445.3018284688678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.643544255379368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 31.996324165557496,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "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": 79,
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1861.0033303173484,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 95.74255598925224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "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": "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:48Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.1778209283398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.946552450271184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "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:9815232c2420f539",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1571.8753694864479,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.11619311992135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.0279839646837,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.42280040640819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:02Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.527697651422,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.87527093406364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 67.84523726457948,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1524.4985638630642,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.00749050094252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1504.1234121905509,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.26204320265185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 83,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "capped_draws": 11,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T06:55:18Z",
      "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": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5548858435868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.63707357709248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.804472558998102,
      "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:2cc2deb36fb4ff9e",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1484.2886571135925,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.23648244618929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 22,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:36:36Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.1284962693098,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.51286102183472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 57.12334745656489,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 95,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 36,
      "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": "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": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.4996298826736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.83800371361828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.11749113942453,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 42,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.241069098968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.513954746621025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1449.778133454939,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.26904479710366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 26,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.3175616005683,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.88151024956463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 42.117366605781385,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T06:55:12Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.39286064408,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.388151856713836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3708349548044,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.35664793074286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-2:ad9fb0aed35ae9e2",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.0068426521739,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.880698337056444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 34,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.7975158584218,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.81671727920589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3307063559512,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.900297866687094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 40.86916081526379,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "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": "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": 37,
      "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": "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8740419822784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.182519323216006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:30:48Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.255627323167,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.171925207422163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:nex-agi-nex-n2-pro:5745a767d889956e",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 33,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T08:55:37Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.5349424095307,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.175958376626816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.3895422530882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.46366360644326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:cohere-north-mini-code:1aa694a2c1eb6ac2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 27,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.1613620278795,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.428307136703403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 46.19324853318743,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1582.9690692214492,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.83931957227835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:gpt-5-4-nano:5c7ad4cb58558f0e",
      "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-5.4-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.996519212638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.26997029285312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "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": 99,
      "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": "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": 55,
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.8056788345384,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.983185125573506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1561.7564985722227,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.441938728209706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-5-flash:9815232c2420f539",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:04:12Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.148668508276,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.737382109924624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:ad9b5d76213eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:01Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.320457917925,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.0964147057753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.51693271964983,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 85,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.4112566798308,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.33968507396859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:stepfun-step-3-7-flash:61eef7ea1025a0f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.4271477634718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.89921383372028,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0428742199645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.01257007858806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:15:01Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.4148214952497,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.31932420897261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 85,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.170150760798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.94559731506889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-1-flash-lite:71cb71219c9b05f8",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T03:46:58Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6208754393567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.157939951088196,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 2,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 165,
      "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": 82,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 19,
      "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": "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": 161,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.413996997494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.665436329086305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.879781663776944,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "capped_draws": 0,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:03:31Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.669383234101,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.67442303505885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 17
    },
    {
      "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:ad9fb0aed35ae9e2",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1501.1308285615892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.1670764313632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 108,
      "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": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.922495957919,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.866644636143132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 70,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.2760299875736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.478769660606087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1486.0440995567778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.14381674077765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 52,
      "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": 1483.6856058732603,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.749828609175978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1481.537434054386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.39355816481966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 181,
      "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": 91,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 181,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.8442918018895,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.85012509642266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.417462425705285,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:04:06Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.5080466753927,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.43239275691567,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 35.37120607977092,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.3790983677727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.91029406876563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.302124119453637,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1482.6080624665635,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.801808670018016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemma-4-31b-it:e2ccce3c75f0de36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 73,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.8974532015468,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.508028292488625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 32.21770585958794,
      "unilateral_faults": 2,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "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": 21,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.516457423049,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.397881427239696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 21,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T03:21:33Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.8183597556254,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.063919114389087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 58.92436501994144,
      "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:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1485.0261871880703,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.287196375393837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.778097636226576,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1465.1792260115858,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.134886304266157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:f8a6e076cfc86cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1463.6610917058263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.534569513484524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:cohere-north-mini-code:1aa694a2c1eb6ac2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 15,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2020263508612,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.82750955564381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.290722098573895,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 85,
      "draws": 217,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.20990283907,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.60477558634496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.58300491269135,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:87a92cb1b6d3a644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1461.3622341881628,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.4947403350086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.290722098573895,
      "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:d605eeb997ce6e73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 14,
      "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": "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7167570727886,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.941506078017632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.300442572851765,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 22,
      "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": "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.4106272254921,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.33720025505064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 35.325478923423304,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 37,
      "draws": 69,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.9050722087582,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.687976243904558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 54.1910171532605,
      "unilateral_faults": 2,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "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": 111,
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.5280885728605,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 82.07879945591797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "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": 72,
      "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": 39,
      "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": "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.5063962519441,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.90020433563501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:10Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1733.9891021907006,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 64.39657956468047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1673.6388165109624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.88434592732646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "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-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1672.1305254535307,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.59740424093167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 61
    },
    {
      "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": 1662.7933410041032,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.02021794771947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:41:58Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.4100113362138,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.384304794269354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1602.5266986191143,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.1027343192657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "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-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1599.0265614912312,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.00203493565957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:34:43Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.8150260457114,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.82300342768883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.831799173767003,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1592.58297021455,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.19986121676889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:87a92cb1b6d3a644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1601.2056239341523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.54275135535724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.52648327229861,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:08:36Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.875101313137,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.214571951063434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:z-ai-glm-5-2:ad9fb0aed35ae9e2",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T00:59:23Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.0888414631513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.08920702046711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-plus:c53556cb68ddc5f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1579.9273324684477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.778489355144025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.29557740277427,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "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:9815232c2420f539",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1549.9264735902525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.30683087113872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56,
      "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": 2,
      "distinct_rated_opponents": 28,
      "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": 32,
      "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 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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.497314720862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.28681973887564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.26463443331983,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:o3:f8a6e076cfc86cf1",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:51:41Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.9217609319278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.02325201056916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-nano:5c7ad4cb58558f0e",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:37Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.6652469966723,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.02166558579286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.486412574268473,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:49:27Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.2837822150532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.70493564691155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemma-4-31b-it:e2ccce3c75f0de36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 39,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:57:18Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.707459487237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.90001524707614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.644997148147095,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:00:43Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0164057321053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.394758803516936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.723103448694367,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:cohere-north-mini-code:1aa694a2c1eb6ac2",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 54,
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.9883204418932,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.6188762763087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.958864622419078,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:stepfun-step-3-7-flash:61eef7ea1025a0f2",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:51:39Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.9069818743108,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.79792203718302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "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": 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-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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:49Z",
      "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": 1490.8078638278364,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.629120841132384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:25:46Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0224962569089,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.32822843528254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3098804014994,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.408119849833696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:25:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0699456891364,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.411492646607414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 35.77525857161958,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 64,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:17:40Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.6096661150161,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.783354882592267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.486995034210185,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "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": 4,
      "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": "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": 122,
      "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": "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5936547110098,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.83100441041674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.080489386472888,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:ad9b5d76213eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1365.2585538585686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.241575056843985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.96298192699785,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 89,
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8203598823284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.320286766981738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.867341638060083,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 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": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:51:41Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.9093913458112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.878231343301803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:nex-agi-nex-n2-pro:5745a767d889956e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T09:17:51Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.5974695891684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.41411822823543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.824399540348086,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "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": 74,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:34Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.8037388255002,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.515428670623326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 38
    },
    {
      "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:71cb71219c9b05f8",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1239.8542944594315,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.8000252646134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1091.7576172341132,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 2.3222203559783994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.37850172271408,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1892.891192538813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 95.42130277416098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "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": 66,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:36Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1862.8922755189858,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 91.70201059215609,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 111
    },
    {
      "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:9815232c2420f539",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1843.3512911845396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 90.25968655583348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:gpt-5-6-sol:a4c19bee132b1ed1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1792.977450720159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.05033494665588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1783.3077264160918,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 84.02163040431354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.7289447776332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 83.06075814643916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-plus:c53556cb68ddc5f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1706.3705923810853,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 74.1617078908414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.779077868707382,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.1398493340357,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 70.68540227201106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:z-ai-glm-5-2:ad9fb0aed35ae9e2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.2045242420968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.68324241888193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:ad9b5d76213eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1656.371302041338,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.21005238359456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.461325131721317,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:f51e041235d08cd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.9350142082228,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.09501277916272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-nano:5c7ad4cb58558f0e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.6886921793475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 65.72313807060283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:o3:f8a6e076cfc86cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:57:23Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.5937026330773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 65.54813103397758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:53Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.115508396417,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.54103500269817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:50Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.0883296357088,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.06281243846746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:11Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.301435818596,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.224644528934874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.951579906118113,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "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": 52,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:42Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.8531936911686,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.445585881637015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 2,
      "distinct_rated_opponents": 33,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T06:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.1002332195922,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.49270207782266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.05007382550214,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:28Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.497978964082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.85823075496087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:49:28Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.0993164354797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.69217513632242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:19Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.154060432485,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.76005671360996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-1-flash-lite:71cb71219c9b05f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:58:16Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.1115221856815,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.375926945379035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_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: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": 60,
      "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": 61,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0865376108627,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.2652285508529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:10:00Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.594146627393,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.08045186567497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.259682442018587,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1384.137730967665,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.11628633456594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:36:51Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.2976003952504,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.71582481684514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 35.67296519906856,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1354.325516280026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.4033081726625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.629534578008435,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemma-4-31b-it:e2ccce3c75f0de36",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1353.3784605717633,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.13197671164298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.633827169132047,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1350.2598567148952,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.860401930611594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.926543555546573,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "distinct_rated_opponents": 24,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.5567794486105,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.16163840382044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 31.00772618643724,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:stepfun-step-3-7-flash:61eef7ea1025a0f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:39Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.6101532628288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.937512179985525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1301.6867097939717,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.46925549155916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:d605eeb997ce6e73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 67,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:25Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.0206728248031,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.92584138096761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.857940612168754,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:cohere-north-mini-code:1aa694a2c1eb6ac2",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1291.4802446130302,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.414777820507236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nex-agi-nex-n2-pro:5745a767d889956e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1253.7861307495552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.078598419102768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.01928828118566,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "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": 70,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 113,
      "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": "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": 1180.5673528891352,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.262080807158373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 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-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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.5748924741924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.32857790093769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.763809051045354,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1762.4042745072609,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.79611330973476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1732.0611905000076,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.86330432028504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1696.3443936235544,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.10196361472715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 35.22106228946894,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.8017327798075,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.58738719657233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "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-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.147005295843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 60.331355683982295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "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-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1641.3171931289405,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.9101347289806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "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",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:28:28Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.5757431946397,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.63713222006284,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 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": 1630.4735516007104,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.08648524326837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:o3:f8a6e076cfc86cf1",
      "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": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1624.3448206991122,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.2984762422112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-5-flash:9815232c2420f539",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:15Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0678904088375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.26204637051112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 85,
      "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": "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.44883752229,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.107484759458345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.357735929582898,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:22Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.1539016254237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.044380476224916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.2161928372725,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.492651104691994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:z-ai-glm-5-2:ad9fb0aed35ae9e2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-31T01:11:18Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.2260932564172,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.862871057100186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "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-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:28:19Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.5171741625923,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.23625448361621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:87a92cb1b6d3a644",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.621615846795,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.72992644564387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.772182566181264,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:34:26Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.0117601373145,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.29733821571418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.242156042632452,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "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": 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-4-5",
        "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:11Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.9594600967189,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.455587919211716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:ad9b5d76213eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 39,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:43:24Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.0811147075337,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.31918562226375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.40923597442238,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 61,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:37:48Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.2820003415932,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.85354162714708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.10987345912298,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-plus:c53556cb68ddc5f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1471.5202267893505,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.70177239399337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.812711145915937,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 86,
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.9013049678656,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.84966093971727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "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:d605eeb997ce6e73",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 111,
      "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": "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.343706908703,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.71668659092171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.457164736907323,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:cohere-north-mini-code:1aa694a2c1eb6ac2",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1451.8589119440062,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.09138610591313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nex-agi-nex-n2-pro:5745a767d889956e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1450.0872590593376,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.53188452999624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.258608963549943,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-nano:5c7ad4cb58558f0e",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:28Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8563076431074,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.013798787289424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemma-4-31b-it:e2ccce3c75f0de36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T21:46:04Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.5635626395624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.35594935305769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.91700367222747,
      "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:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1401.2822756940366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.2955991645047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5948380411917,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.08163384316626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.45170261998272,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.472304078443,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.25781838363284,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.941634169259466,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1307.8916232961728,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.202311210174184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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": 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": "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.5590178307139,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.97030061327731,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1196.149393725581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.786907510390217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 10
    },
    {
      "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:f51e041235d08cd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1165.7290719890677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 12.422397885640807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-1-flash-lite:71cb71219c9b05f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:12Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1052.903259206907,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 1.18683615794815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "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": 101,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1902.1030786263232,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 82.83097754139442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.759161709357059,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "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": 1882.0961693922998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 80.48164573606203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-fable-5:0ee928b7e2ba2cec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1814.5336004592846,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.22544650832927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 17,
      "max_score": null,
      "measured_at": "2026-08-04T21:52:45Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.2666943887314,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.00313139343699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-sol:a4c19bee132b1ed1",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1778.443049602078,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.83663626822397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:87a92cb1b6d3a644",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1674.6742605175516,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.725778913783415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.291258434495777,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 17,
      "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": "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.1866708150255,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.848011910482846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-nano:5c7ad4cb58558f0e",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1610.5029346193264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.084198694140696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-5:a02992da372e3456",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1605.807541988619,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.93181649730258,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-terra:2cc2deb36fb4ff9e",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1485.5625871021477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.5924272304032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:o3:f8a6e076cfc86cf1",
      "capped_draws": 63,
      "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": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1466.4297670164335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.624425793989726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4:a414af8b62b805e3",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.2219261759235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.292543079332418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:openai-gpt-oss-120b:4b308bb013f8b4a4",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1444.8116248114163,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.95538217774586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:f51e041235d08cd6",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.809420939187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.28574181894595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-1-flash-lite:71cb71219c9b05f8",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.5502098452275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.179696020170926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-mini:049d015a8e550155",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1436.6611574632266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.91395572652641,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-max:098f6efae2428482",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 36,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1447.77340818449,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.4196347480646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.976534673506283,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 71,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:25:51Z",
      "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": 71,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.2338469609456,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.407921076039756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.175565098878963,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-luna:ee18bd1934805efa",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.4023399340574,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.014259316222454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-sonnet-5:e275ffc395eccdfb",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 83,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.2683033126514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.602617521323882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-8:7cfd41fe2ad183d6",
      "capped_draws": 82,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.9709089457906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.170508876258452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:36:46Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.7671715437525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.132200293916647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.79047988958712,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 44,
      "draws": 139,
      "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": 23,
      "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": "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.586080274788,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.037611680027343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 32.561240097148016,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ae403b862ae3c43a",
      "capped_draws": 140,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.6670918396599,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.99912090816997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.818262520573185,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 116,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 23,
      "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": "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.7827706058372,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.963666797879824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.836607386351783,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-build-0-1:eaa5f1de94903ae7",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.7720758672476,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.918992285254213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.044184037997496,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:minimax-minimax-m3:e098069f6f03fd6c",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4684130812043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.882984936169017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.044184037997496,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-2:ad9fb0aed35ae9e2",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.9759189337483,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.83019830376679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-plus:c53556cb68ddc5f3",
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1432.9907321597134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.40155383767231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.772182566181264,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5:132f7789eb1666ec",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 65,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.6262448047164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.539897931555156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.73327639367909,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5:6a739837557f0356",
      "capped_draws": 54,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.3551553183834,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.462701167505323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:cohere-north-mini-code:1aa694a2c1eb6ac2",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 78,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.6272805817675,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.369345026768944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.865877260366762,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:ad9b5d76213eb171",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 73,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.5044432580917,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.841275546599956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.779077868707382,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash:9815232c2420f539",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T02:54:30Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.2923757001072,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.20229853735902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meituan-longcat-2-0:4fdb70c2a982db02",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 41,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.0654464521704,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.843454373359577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 51.44099895136409,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nex-agi-nex-n2-pro:5745a767d889956e",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:33:48Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.3292533208191,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 5.696416759421026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.170873961698575,
      "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": 69.63250431033174,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 302,
      "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": "2026-08-05T05:33:21Z",
      "losses": 246,
      "max_score": 99.17317608622864,
      "measured_at": null,
      "min_score": 43.10391328842407,
      "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": 1389,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.5745090558803,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 67.34634456096008,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 841
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4:a15eecb9d5ad7173",
      "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": 0.15985749999999999,
        "mean": 0.09356500000000001,
        "median": 0.07461,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7485200000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.74604881905605,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 262,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 99.95680517171921,
      "measured_at": null,
      "min_score": 22.571342246704436,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 708,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.6063071993929,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 50.74604881905605,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 292
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.97393
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.145924913466516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 267,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 213,
      "max_score": 68.15920342920347,
      "measured_at": null,
      "min_score": 28.975930507597035,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.7863391495157,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.145924913466516,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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-2026-07-30": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.6080262000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.11650001410064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 221,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "2026-08-05T05:28:59Z",
      "losses": 171,
      "max_score": 68.5646741796879,
      "measured_at": null,
      "min_score": 20.180463665789603,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.1331996248377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.11650001410064,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 308
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.2628250000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.49013596853746,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 157,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 187,
      "max_score": 66.52956277651462,
      "measured_at": null,
      "min_score": 22.761732969686722,
      "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": 608,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.9957511032883,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 44.96378159356898,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "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",
        "failed_cell_count": 1,
        "max": 0.147405,
        "mean": 0.12146437500000001,
        "median": 0.124865,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.069485
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 44.076052399600464,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 189,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 235,
      "max_score": 62.3891044858804,
      "measured_at": null,
      "min_score": 27.998655419890518,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.22877695441,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.79712153869371,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 272
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "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": 0.3591713804000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 40.619224127384456,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 376,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 399,
      "max_score": 64.32999385511812,
      "measured_at": null,
      "min_score": 20.60128829346809,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1140,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.4359727217739,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 40.619224127384456,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 365
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "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-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063375
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 40.807182043299505,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 298,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 240,
      "max_score": 52.193541012565454,
      "measured_at": null,
      "min_score": 24.606530359301495,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.2289950075524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 39.6231022171695,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 212
    },
    {
      "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-2026-07-30": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.5947036
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.417956094564275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 182,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "2026-08-05T05:36:22Z",
      "losses": 164,
      "max_score": 62.895170182688986,
      "measured_at": null,
      "min_score": 6.748867164434723,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.3840324485354,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 39.417956094564275,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 220
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "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": 0.12449953100000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.574001935890315,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 232,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": "2026-08-05T04:18:01Z",
      "losses": 212,
      "max_score": 68.86134465387879,
      "measured_at": null,
      "min_score": 25.40534241954475,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 660,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.285671438715,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 39.24188483030178,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "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": 39.86320548854211,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 211,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 223,
      "max_score": 66.08924139036272,
      "measured_at": null,
      "min_score": 25.366216398962596,
      "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": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6865413148555,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.554425102550525,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:xiaomi-mimo-v2-5-pro:0671298d7843d215",
      "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": 39.644261976279005,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 136,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:19:05Z",
      "losses": 199,
      "max_score": 51.181270461651444,
      "measured_at": null,
      "min_score": 29.295127175194555,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 548,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.1712755621945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.14552881709858,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.4575640000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.374773927607926,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 257,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 262,
      "max_score": 60.675097556373565,
      "measured_at": null,
      "min_score": 12.488827301220297,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 729,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.569278532663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.374773927607926,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 210
    },
    {
      "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": 38.20459574532886,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 415,
      "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": "2026-08-05T05:33:39Z",
      "losses": 415,
      "max_score": 52.594117482982824,
      "measured_at": null,
      "min_score": 25.188695148003053,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1212,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.019071665591,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.76028850836054,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 382
    },
    {
      "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": 37.124225832861065,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 390,
      "eligibility_flag": true,
      "entry_count": 30,
      "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": "2026-08-05T05:33:25Z",
      "losses": 330,
      "max_score": 60.72491770132335,
      "measured_at": null,
      "min_score": 18.932093277185512,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1019,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.3812259706854,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.53004649639792,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "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-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.374699430120664,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 344,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 179,
      "max_score": 48.376451029853435,
      "measured_at": null,
      "min_score": 24.844878577648164,
      "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": 678,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.5937919370792,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.147621152119854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 36.12279181493238,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 473,
      "eligibility_flag": true,
      "entry_count": 32,
      "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": "2026-08-05T06:56:02Z",
      "losses": 344,
      "max_score": 49.20301710581384,
      "measured_at": null,
      "min_score": 18.71384108753165,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1153,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.454333940451,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.12279181493238,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 336
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-nano:b6b1837db41ddd7f",
      "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-2026-07-30": 27
        },
        "run_count": 16,
        "token_priced_attempt_count": 27,
        "total": 0.14744575000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.33172325240589,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 331,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 430,
      "max_score": 57.22166014466003,
      "measured_at": null,
      "min_score": 17.314483317000402,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1114,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.9955615933582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 35.671687916445855,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 353
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:minimax-minimax-m3:8a90e1100fdd5510",
      "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": 0.20304798
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.89690270596678,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 133,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 224,
      "max_score": 51.404796674852406,
      "measured_at": null,
      "min_score": 20.685292976640326,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 580,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.5217020426765,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 35.26704180309219,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:tencent-hy3-preview:b7d753c6f1ae2a1b",
      "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": 36.02354942102359,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 238,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 71.41435556334146,
      "measured_at": null,
      "min_score": 18.633293372543374,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 534,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9282732895588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 33.523690133309174,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "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": 34.086057407750324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 512,
      "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": 521,
      "max_score": 51.81464157035592,
      "measured_at": null,
      "min_score": 13.631497595831043,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1404,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.195016070938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.96695113357302,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 371
    },
    {
      "admitted_plugins": 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": 0.58845395
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 35.40708035253855,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 380,
      "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": 491,
      "max_score": 63.27779754414018,
      "measured_at": null,
      "min_score": 15.88003173451959,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1206,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.03304472824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.950001022690856,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 335
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "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": 0.06890521579999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 35.45466399034528,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 410,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 580,
      "max_score": 47.98241645206621,
      "measured_at": null,
      "min_score": 21.508488342824627,
      "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": 1472,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.1005416126695,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 32.28431302119879,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:515ae6ce8831a75d",
      "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": 0.3891924
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 33.84070816163852,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 172,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 205,
      "max_score": 53.84911215292571,
      "measured_at": null,
      "min_score": 13.294011760456632,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 512,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5577122850716,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.779958466828784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemma-4-31b-it:b90133150b523b66",
      "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": 30.588833048590292,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 186,
      "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": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": [],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:11Z",
      "losses": 253,
      "max_score": 44.46648998691777,
      "measured_at": null,
      "min_score": 14.548948613994082,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 602,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.1894178321834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.43243623086199,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "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-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.1470525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.63144123682781,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 336,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 261,
      "max_score": 39.705796487312476,
      "measured_at": null,
      "min_score": 10.185410895530666,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 724,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.8559772496237,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.63144123682781,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:c286ec53824be443",
      "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": 26.078342532879816,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 248,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 256,
      "max_score": 36.22574841026145,
      "measured_at": null,
      "min_score": 9.943666245746922,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.5434369698607,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 25.222143870782425,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-plus:f3ff5118ffc9392d",
      "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": 27.30904138637005,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 175,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 252,
      "max_score": 42.83286645498502,
      "measured_at": null,
      "min_score": 8.83134021951195,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 543,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.416172883214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.676504513388153,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 10,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:inclusionai-ling-3-0-flash:5505b445ff32e087",
      "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": 27.637609971091333,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 662,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 433,
      "max_score": 40.20061892348984,
      "measured_at": null,
      "min_score": 19.463800160566905,
      "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": 1298,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.515121751544,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.573696377139072,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 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": 25.05457754739122,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 127,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": "2026-08-05T05:12:01Z",
      "losses": 294,
      "max_score": 44.426727828824966,
      "measured_at": null,
      "min_score": 11.848074548273324,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 531,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.850679973971,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 24.231990922169725,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "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": 0.038815,
        "mean": 0.02196775,
        "median": 0.0196975,
        "min": 0.016152,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.175742
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.928427773195263,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 302,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 335,
      "max_score": 37.02321330902676,
      "measured_at": null,
      "min_score": 0.5457336893360095,
      "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": 713,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.1105602032653,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 0.125,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 19.928427773195263,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-1-flash-lite:b8b61f8ed8571a70",
      "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": 19.163277618622363,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 208,
      "max_score": 46.321870346065246,
      "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": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.405759656805,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 17.038831009027934,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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-2026-07-30": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 47.75501155028078,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 26,
      "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": "2026-08-05T05:27:30Z",
      "losses": 22,
      "max_score": 47.75501155028078,
      "measured_at": null,
      "min_score": 47.75501155028078,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.321654013368,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.75501155028078,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-sonnet-5:3a7fef9d726efa8f",
      "capped_draws": 0,
      "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-2026-07-30": 1
        },
        "recorded_attempt_count": 2,
        "run_count": 1,
        "total": 0.09014
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 44.83323249072341,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": 1,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "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": "2026-08-05T05:37:42Z",
      "losses": 10,
      "max_score": 44.83323249072341,
      "measured_at": null,
      "min_score": 44.83323249072341,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6057722063917,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 44.83323249072341,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "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": 37.689134564680714,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 55,
      "eligibility_flag": false,
      "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": "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": "2026-08-05T06:57:11Z",
      "losses": 124,
      "max_score": 61.23827813661711,
      "measured_at": null,
      "min_score": 22.033193461986272,
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.0006601656364,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 31.69265814945488,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:mistralai-mistral-medium-3-5:d3aa61e49e4992f8",
      "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": 0.3439575
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.37784506240003,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 107,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 44.576050565533166,
      "measured_at": null,
      "min_score": 23.94602226083568,
      "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": 401,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.1679734426546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.749103092373506,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "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": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.49125409606727,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 291,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 193,
      "max_score": 59.024723737278265,
      "measured_at": null,
      "min_score": 21.874533667805792,
      "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": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.991222349984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.051332748112884,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "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-2026-07-30": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.993705903564226,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-05T05:37:32Z",
      "losses": 134,
      "max_score": 44.1151076188509,
      "measured_at": null,
      "min_score": 24.102373476112174,
      "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": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.6231360847037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 27.744289020242476,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:cohere-north-mini-code:d5fb08672532172f",
      "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": 25.767952587353744,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 192,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 251,
      "max_score": 26.27689482403025,
      "measured_at": null,
      "min_score": 24.96235519414845,
      "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": 530,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.2155569895012,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 19.266038248032807,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4:a15eecb9d5ad7173",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2000.7945640968424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 99.95680517171921,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:tencent-hy3-preview:b7d753c6f1ae2a1b",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.2538039468136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.41435556334146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 101,
      "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": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1719.3151008210912,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 70.20827359206642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.3768736235092947,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-nano:b6b1837db41ddd7f",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:01:18Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.4391919461466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.22166014466003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.383178954266332,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 47,
      "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": 109,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.5902539682866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 56.353504319456164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.9231294622796127,
      "unilateral_faults": 1,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4078988417914,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.02675103959072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:515ae6ce8831a75d",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:24:08Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.046272202658,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.84911215292571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.0311336651146,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.58101009021854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:05:30Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.7694478579945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.193541012565454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "capped_draws": 11,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:07:28Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.171019743832,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.9309965364074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:minimax-minimax-m3:8a90e1100fdd5510",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:28Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.4553724122525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.404796674852406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 79,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.6020170542076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.46705421247383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.812711145915937,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "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": 113,
      "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": 102,
      "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": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.7215971564779,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.20338899029913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.279970601756496,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 90,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.5640194755229,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.376451029853435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 82,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:59Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.7086701736835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.082101410112614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.0601607140728,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 152,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:58:44Z",
      "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": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.3998585358459,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.98241645206621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.833995575469414,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:27:30Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.321654013368,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.75501155028078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T04:18:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.5540474275292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.53770120402753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-sonnet-5:3a7fef9d726efa8f",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:42Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6057722063917,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.83323249072341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8
    },
    {
      "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:d3aa61e49e4992f8",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1483.4317022040432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.576050565533166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:google-gemma-4-31b-it:b90133150b523b66",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-05T03:13:53Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.4739373802697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.46648998691777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 50,
      "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": 56,
      "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": "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3529275927908,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.4397189219023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.245147965872874,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 25,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.8178118795715,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.428677925307234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:inclusionai-ling-3-0-flash:5505b445ff32e087",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 122,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 114,
      "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": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.2355596845537,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.20061892348984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_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": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:0671298d7843d215",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1427.5356647847705,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.853074260758646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 240,
      "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": 114,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 93,
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.5389657970331,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.76737781757434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.74653294141069,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 41,
      "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-3.6-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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:22Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.2915126707596,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.95822410059949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.101841152647836,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:15:42Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.215360433307,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.877002635313595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1362.3304641440059,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.981232011417283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-plus:f3ff5118ffc9392d",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1351.2113457571206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.350197668676998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "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": "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:51:26Z",
      "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": 1366.1615915517368,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.575915709416066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.698553251899696,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 29,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.3403044689535,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.71108537090077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 39.36952453316905,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:cohere-north-mini-code:d5fb08672532172f",
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 104,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 101,
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.3132286826562,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.96235519414845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.817566863743322,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1277.2755591791679,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.385721389270085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 14
    },
    {
      "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": 1213.859923509973,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.88003173451959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:b8b61f8ed8571a70",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1181.3686609045587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 11.482216539302486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 178,
      "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": 89,
      "draws": 70,
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.5008318334221,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.15318329442692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.7441141687189,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.456640462802426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 49,
      "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": "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.1585038473304,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.957237052457256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:0671298d7843d215",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.0331584380926,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.295127175194555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 74,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9783604804352,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.975930507597035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 56,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T00:00:10Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2258908916226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.998655419890518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:03:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.6324167926382,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.610135698210527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.248896520903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.40534241954475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 104,
      "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": 51,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.448849917776,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.188695148003053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8084557546495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.844878577648164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-1-flash-lite:b8b61f8ed8571a70",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1482.8419989760441,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.513374734358962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 82,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.3176618766922,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.39608248464808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.8760079780336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.33755198695994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-plus:f3ff5118ffc9392d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4062283762817,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.06441481400451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-nano:b6b1837db41ddd7f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.396359014816,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.617486633688323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-flash:c286ec53824be443",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.1514124728146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.329211401413826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 82,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.565751019137,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.086494711467868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1470.3374865351009,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.761732969686722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2125218481146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.726527476576994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4:a15eecb9d5ad7173",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.3031221858107,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.571342246704436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:inclusionai-ling-3-0-flash:5505b445ff32e087",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1459.7462631719882,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.380386424640683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1464.2426317683783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.874533667805792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 70,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.4359726589596,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.690874544258786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:minimax-minimax-m3:8a90e1100fdd5510",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1462.4496711139095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.685292976640326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 117,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:32Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.2688292024814,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.60128829346809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.755723064737715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "draws": 74,
      "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": 6,
      "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": "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.8090974764614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.180463665789603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 35.491466493865985,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 56,
      "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": 4,
      "distinct_rated_opponents": 28,
      "draws": 114,
      "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": 7,
      "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": "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.721647002374,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.22178430751722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 45.645487332256415,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 56,
      "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": 4,
      "distinct_rated_opponents": 28,
      "draws": 115,
      "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": 5,
      "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": "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.9288912413258,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.71384108753165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 46.19324853318743,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:tencent-hy3-preview:b7d753c6f1ae2a1b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.0917807935598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.633293372543374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "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": 2,
      "distinct_rated_opponents": 19,
      "draws": 37,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:25Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.8982190001293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.54676360453859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 68.15703845127177,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 2,
      "distinct_rated_opponents": 19,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 15,
      "max_score": null,
      "measured_at": "2026-08-03T13:45:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.7566230465538,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.24738547213113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 39.80145244019624,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4:a15eecb9d5ad7173",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.3083636563829,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 56.324293275397885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 172,
      "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": 86,
      "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": "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": 54,
      "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.1482186314154,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.09590571829045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "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": "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.872973253256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.893839142278445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.180010894095469,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 27,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 30,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.8397181307937,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.74207105225406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-03T13:39:17Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.7262366492885,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.55730234033761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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-4-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.8257098927816,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.90185636252289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 27,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:27Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.2159632399143,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.89856102744325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.51471483712608,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 34,
      "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-3.6-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": 38,
      "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": "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.0142504521068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.34197525944053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 39.07360537523139,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-nano:b6b1837db41ddd7f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.3524419563448,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.304281381765435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 56,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-31T01:34:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.9632361068366,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.18649842669409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.507220868368073,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:minimax-minimax-m3:8a90e1100fdd5510",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:55:23Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.8755147233076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.18446384616218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.7237122491786,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.860150083019626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "capped_draws": 1,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:24:36Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.915508520607,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.02321330902676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.1084595149894,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.328921102635334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 78,
      "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": "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": 46,
      "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": "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.8627401134768,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.72130392267117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.7223548257912,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "capped_draws": 7,
      "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-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:23:57Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.647103601243,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.64775037461809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:tencent-hy3-preview:b7d753c6f1ae2a1b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2133962405546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.28541772823972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:37:58Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.199816272659,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.27444521040391,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:0671298d7843d215",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:54:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.3589845100641,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.0378996400634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:07:00Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.3899699523217,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.476184640834816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-flash:c286ec53824be443",
      "capped_draws": 0,
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:23:15Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.523896395089,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.578832477807513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "capped_draws": 6,
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.7587628203037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.549441181835455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 77,
      "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": 51,
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.7672192302994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.14500345598673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.493504750482622,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:515ae6ce8831a75d",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.2361193788938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.69906909498186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.28947900497,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.516168554327326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:inclusionai-ling-3-0-flash:5505b445ff32e087",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.9748824540438,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.666335927907475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:26:19Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.7495647402448,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.15319521590135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 48.07227218399459,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T02:39:33Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.9018046900726,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 6.748867164434723,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 37.551153208577354,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "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": "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": 22,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.3561576652844,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.225562918867894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "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": 99,
      "draws": 79,
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.461981055621,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.10391328842407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 48,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8865414749796,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.16676257859201,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T03:59:31Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.7252140790329,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.462569717437304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 37.89405657207563,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "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-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.1627836273447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.25696174455382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1509.0423085525442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.50597954900976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:tencent-hy3-preview:b7d753c6f1ae2a1b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.5599956004069,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.952233073927275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:inclusionai-ling-3-0-flash:5505b445ff32e087",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 6,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.113459457968,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.35713798385482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.714578014611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.73976498521204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.124241049220077,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:515ae6ce8831a75d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.4747006526225,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.34819561268509,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.875178692428,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.726131179809055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemma-4-31b-it:b90133150b523b66",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.3691141009099,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.480599265900732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1490.9532680536443,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.313916897298004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:gpt-5-4:a15eecb9d5ad7173",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5133398135404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.231477991886752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:31:22Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.2045172936457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.78875211304417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.65987454855759,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "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-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:33:21Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.0322829267293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.965940546014295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0635006450743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.853421449925953,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 38,
      "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": 4,
      "distinct_rated_opponents": 19,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 16,
      "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": "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": 97,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.8762960785205,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.82991502575947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 57.47663899604805,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "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": 86,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.096664771153,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.247391403906573,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:24:08Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.7557500321805,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.82354680882762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-7-plus:f3ff5118ffc9392d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1281441770377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.51487556975524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1469.2709415655665,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.37461139902881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44,
      "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": 4,
      "distinct_rated_opponents": 22,
      "draws": 102,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.3216445459439,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.53021032625603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 47.60557679671052,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "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": 2,
      "distinct_rated_opponents": 14,
      "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": "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": 7,
      "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": "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.55224106402,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.564742978629265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 50.78635697673178,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "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": 2,
      "distinct_rated_opponents": 17,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-04T21:56:09Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.114574817395,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 11.848074548273324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 55.86164620406626,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:deepseek-deepseek-v4-flash:c286ec53824be443",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1376.1312280226116,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 9.943666245746922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 230,
      "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": 115,
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1965.1031344087517,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 86.53651167123698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 206
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4:a15eecb9d5ad7173",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.5579433554326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.38417347397768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1662.6720777987493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.70473458705692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.606346995783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.095684875993925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 28.714783570323423,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "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": 96,
      "draws": 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": 70,
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.9598470652513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.594117482982824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:515ae6ce8831a75d",
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6892957530818,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.31857245670056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-03T10:29:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.219415390376,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.16554962876789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "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-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:14:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.1507673596157,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.52029893343254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 60,
      "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": 4,
      "distinct_rated_opponents": 30,
      "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": 60,
      "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": "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.384263429241,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.10663380914288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 39.515204390048446,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:34Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.2854909074172,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.21778129130201,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "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": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-04T23:21:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.3995628419666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.85922359902054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9857641872218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.618288762349096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.468842775200363,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 127,
      "draws": 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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "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": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.79079258633,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.47068028863717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.174752555128595,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-plus:f3ff5118ffc9392d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:37:44Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.6944028280163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.83286645498502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:29:18Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9159982859114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.54851301568021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.8352266808859,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.07016716141857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 46.518758273283815,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:minimax-minimax-m3:8a90e1100fdd5510",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.2367408862915,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.69149287984802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:0671298d7843d215",
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2800289578179,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.62067621907194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.2181246632692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.82165124902767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-flash:c286ec53824be443",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.9492077155455,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.51172275800236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 54,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0141768671742,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.33051290926278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:mistralai-mistral-medium-3-5:d3aa61e49e4992f8",
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.2176833271508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.0464884077659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:tencent-hy3-preview:b7d753c6f1ae2a1b",
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.0311903903728,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.009668601208,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "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": 2,
      "distinct_rated_opponents": 13,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T03:10:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.6546307873011,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.50243701119809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 49.26384793916254,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "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": 105,
      "draws": 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": 139,
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.3985429518834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.736801434866358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "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-5.4-mini",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:40:16Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.5279664398565,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.935953546031328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "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": 2,
      "distinct_rated_opponents": 28,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.272383068994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.302124280326495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 28.406749398777613,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 46,
      "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": 4,
      "distinct_rated_opponents": 22,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-08-05T03:18:11Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.3724729141295,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.932093277185512,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 43.40581686499769,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-nano:b6b1837db41ddd7f",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1236.6737860033923,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.314483317000402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:b90133150b523b66",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1206.244527485814,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.548948613994082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 178,
      "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": 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": "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": 126,
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1198.143112700935,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.631497595831043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.573428145379982,
      "unilateral_faults": 4,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-1-flash-lite:b8b61f8ed8571a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:34:49Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1199.66391873774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.498926473385124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "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-4.1",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 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": "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": 1184.8550619458447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 12.488827301220297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1059.7162217483137,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 0.5457336893360095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1924.0542264240664,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 99.17317608622864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4:a15eecb9d5ad7173",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 8,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.2495360528883,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 72.48046758902608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1642.2089240234834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.86134465387879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T20:22:51Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.5598024695696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 64.32999385511812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "capped_draws": 0,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 29,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0538051265532,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.619735110933746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.7623852068155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.23827813661711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 37.61757338116737,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 46,
      "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": 4,
      "distinct_rated_opponents": 23,
      "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": "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:58Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.5740263790071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 60.72491770132335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 48.41404858347368,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 34,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.774398115172,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 60.675097556373565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 2,
      "distinct_rated_opponents": 24,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:14Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.000524633293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.81921687216023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.08892829743688,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "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": 2,
      "distinct_rated_opponents": 21,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:40Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.1505318997167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.264113485188496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 40.79847712741413,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-nano:b6b1837db41ddd7f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.7080123574883,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.921126092380206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.7753885573785855,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "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": 102,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 103,
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2567073413627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.81464157035592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.2120790081366986,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 40,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.2036667060856,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.13788519283952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:0671298d7843d215",
      "capped_draws": 0,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:47:39Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8800041097018,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.87752410093403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 131,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.2396680114384,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.71129462396064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.404615867627035,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-1-flash-lite:b8b61f8ed8571a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:02:44Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4590360383802,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.321870346065246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:04:35Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7393326842414,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.266797985099174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:57:32Z",
      "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": 1417.4757599964255,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.23874521686571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 2,
      "distinct_rated_opponents": 30,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.073566639609,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.426727828824966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 39.29025629120688,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 58,
      "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": 4,
      "distinct_rated_opponents": 29,
      "draws": 19,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:31Z",
      "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": 151,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8525286946704,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.68827725343043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 38.69042571037485,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "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:d3aa61e49e4992f8",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1378.8243454602684,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.942819015465346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemma-4-31b-it:b90133150b523b66",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1373.38682774224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.63225251749573,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 110,
      "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": 53,
      "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": 56,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.1456650071532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.80306201224402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1365.4665711563578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.705796487312476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46,
      "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": 2,
      "distinct_rated_opponents": 23,
      "draws": 18,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.8542682799737,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.04625714839305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.2356618633981,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "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:515ae6ce8831a75d",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1295.593141086351,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.82099690512065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1279.3223943837968,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.541429111812185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 99,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-plus:f3ff5118ffc9392d",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1276.4806787457837,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.26055359128659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 1270.3210113293824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.784727597962565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:20:18Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.588396713997,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.534623279080066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-flash:c286ec53824be443",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1177.8349760515114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.56075363575773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:5505b445ff32e087",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1170.0753284490197,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.463800160566905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "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-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1036.920602437529,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 4.569710286459858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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-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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1835.2604164135125,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 79.18257070094032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1705.0967292013736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.08924139036272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:35:22Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.940513626986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.3891044858804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "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": 2,
      "distinct_rated_opponents": 18,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.4839434630712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.78676996714175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 51.90421938533743,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:15:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.70258494576,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 59.024723737278265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 40,
      "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": 4,
      "distinct_rated_opponents": 20,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:30:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6202653307714,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.047608947568996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 50.41666726374335,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 35,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1603536781683,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.294481025847816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:0671298d7843d215",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:50:32Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.93981257272,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.181270461651444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 203,
      "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": 96,
      "draws": 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": 106,
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.4789026376432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.644464757221996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.759599509820776,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 45,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.1610657525957,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.41579682248144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 51,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.1958341337388,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.231533682902075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 48,
      "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": 4,
      "distinct_rated_opponents": 22,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.5031817176923,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.20301710581384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 46.13344768758128,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:43Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.539579591432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.24855218994896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.409685569755814,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:02:22Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.5057890966405,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.768651176435434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:28:45Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.6131615979011,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.504203648777164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.5100071416261,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.1151076188509,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 41.25700210070024,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "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": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 99,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.7639380942178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.888503192541094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.773447205193634,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:43:34Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.8694948539608,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.59938350830355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:minimax-minimax-m3:8a90e1100fdd5510",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1440.0116718921627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.64455151180685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58,
      "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": 2,
      "distinct_rated_opponents": 29,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T06:57:11Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8399822560605,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.98262964892139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.698553251899696,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-flash:c286ec53824be443",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1406.6667442109426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.22574841026145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T22:56:47Z",
      "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.0218716764423,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.12023152301707,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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:b6b1837db41ddd7f",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1377.7199812397787,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.70010205201074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 48,
      "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": 2,
      "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": "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:23:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.7784399022385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.479903919492436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.08892829743688,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "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": 1364.5064243167951,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.460482495895945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:cohere-north-mini-code:d5fb08672532172f",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1302.1104543187066,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.064607743882533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:gpt-5-4:a15eecb9d5ad7173",
      "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",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1299.2820176175837,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.63023441070387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 36
    },
    {
      "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:b90133150b523b66",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1288.3055324602838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.48890361547792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 48,
      "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": 2,
      "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": "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T04:31:06Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.7021143336742,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.789612194123116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 35.48369970321018,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "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:515ae6ce8831a75d",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1179.1916405345034,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.294011760456632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 87,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1172.2216045615141,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 12.928888178071984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 1,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1144.1874341325886,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 10.185410895530666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:f3ff5118ffc9392d",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1131.5762374150424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 8.83134021951195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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:b8b61f8ed8571a70",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1045.6951836273022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:31Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1801.6806806916547,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.5646741796879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.62217943844404,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-5:a67c075084c51fde",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.1633732381583,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.15920342920347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-8:e749aa1f48ca6c9f",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.4200337972638,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.52956277651462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 54,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.2256601683764,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.27779754414018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-04T23:19:16Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.6482757361791,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.895170182688986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.84785372359809,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "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-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": 48,
      "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": "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.752162859162,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.60650013104014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.43756316443626,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-2:50e10bb40b0a2924",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.1255280580322,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.24817449486797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.473660794592899,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-sol:44986b7a108cb716",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1539.1028287524625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.5657581912891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-nano:b6b1837db41ddd7f",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.6791586355407,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.2429231453361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.221225597086458,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-pro:1e42cfb05da3ca13",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1525.8670668329498,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 38.37160182164898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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-m3:8a90e1100fdd5510",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 1523.101241228136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.77081834649088,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4:a15eecb9d5ad7173",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.841570816661,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.38959639303247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:515ae6ce8831a75d",
      "capped_draws": 76,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.6728163873909,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.55499914859909,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-5:52fd02350122e19f",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4705060316537,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.041252381178502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemma-4-31b-it:b90133150b523b66",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.356567823582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.91580429175553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8580197603374,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.878320723885658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:tencent-hy3-preview:b7d753c6f1ae2a1b",
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4194727656443,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.84632818688169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-luna:b74839249816e1a6",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.4850403755702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.612132302735073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-mini:fd83cdce6f366a36",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-04T06:58:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4052725343836,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.577174727119328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nex-agi-nex-n2-pro:311e8890642ce48c",
      "capped_draws": 94,
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0354741384447,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 27.126778881865853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:inclusionai-ling-3-0-flash:5505b445ff32e087",
      "capped_draws": 262,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 122,
      "draws": 262,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.9452372916912,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.757380406088267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-flash:c286ec53824be443",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.5465939205094,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.3984628011689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 189,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3405534391286,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.29547231816128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:cohere-north-mini-code:d5fb08672532172f",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.2229879671406,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.27689482403025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 37,
      "draws": 134,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:50:28Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.316209227975,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.899207454188396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.68291638854062,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 41,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 27,
      "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": "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3383987718696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.440155577244205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.54983807626827,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-7-max:1b20ba19a3b12637",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.188024322118,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.366216398962596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-4-1:1d5d48e7089da1ff",
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.6268161240855,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.257408425790306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-terra:22f0857599768257",
      "capped_draws": 72,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.6697828592557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.606530359301495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 2,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:50:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.7879644482614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.102373476112174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 41.964285714285715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:mistralai-mistral-medium-3-5:d3aa61e49e4992f8",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.1981627791558,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.94602226083568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 46,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:32Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.880964666142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.28639305487321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 51.22404724625551,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": "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": 16,
      "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": "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.745642412368,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.033193461986272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 51.22404724625551,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-5:b5ae3a0690e3e659",
      "capped_draws": 130,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 130,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.826643434552,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.508488342824627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.106579720176814,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.66097
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 84.62938089750429,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 94,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 66.9670189086873,
      "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": 712,
      "rating_method": "sequential_elo",
      "raw_elo": 1840.6422584145398,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 84.62938089750429,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 502
    },
    {
      "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": 22.074450000000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 80.80364109715514,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 63,
      "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": 157,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 63.096152664379886,
      "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": 894,
      "rating_method": "sequential_elo",
      "raw_elo": 1827.2514920520223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 76.71614536377726,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 674
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "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": 3.2933475,
        "mean": 2.642580625,
        "median": 2.681945,
        "min": 1.562975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.140645
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 72.00166756452465,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 136,
      "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-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 119,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 31.89608232157542,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.57144525601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 72.00166756452465,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 441
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.915325,
        "mean": 10.059243749999998,
        "median": 10.0094025,
        "min": 8.401555,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 80.47395
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.26422692833881,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 79,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 201,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 20.34202322749009,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.1981625117853,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 66.26422692833881,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 420
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 67.14610422168701,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 124,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 144,
      "max_score": 94.05837364506577,
      "measured_at": null,
      "min_score": 15.142060466906322,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.5181167726118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 64.94157743754894,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 368
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "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-2026-07-30": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.449889999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 67.09931744185045,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 83,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:23:19Z",
      "losses": 181,
      "max_score": 85.7032381321606,
      "measured_at": null,
      "min_score": 45.72757509137996,
      "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": 658,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.9652062921778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 64.89632675143649,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "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-2026-07-30": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.32801249999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.51299956858802,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 152,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 231,
      "max_score": 78.97727049438612,
      "measured_at": null,
      "min_score": 42.88844588724325,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 708,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.6847586482775,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 55.51299956858802,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 325
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "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": 4.987857,
        "mean": 3.1645696249999995,
        "median": 3.0710854999999997,
        "min": 1.985613,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 28.806540999999996
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 51.77671506081652,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 156,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 234,
      "max_score": 81.11440057033718,
      "measured_at": null,
      "min_score": 15.787023585925473,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 698,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.1822393361529,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 0.1111111111111111,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 50.27433825612214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 308
    },
    {
      "admitted_plugins": 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-2026-07-30": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.5964052000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.0057833578023,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 123,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-05T05:37:07Z",
      "losses": 183,
      "max_score": 66.94474034970983,
      "measured_at": null,
      "min_score": 17.698293904601133,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 602,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.0476251439297,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 47.0057833578023,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 296
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "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": 7.6379623500000005
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 47.06945590526891,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 146,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 4,
      "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:28:59Z",
      "losses": 224,
      "max_score": 74.49579059518622,
      "measured_at": null,
      "min_score": 34.36861595666778,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Google",
      "provider_key": "google",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 755,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.5567830819143,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.53205466482623,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 385
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-pro:e4ede0086e6579b7",
      "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": 44.28286266599719,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 132,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 242,
      "max_score": 71.11107962938964,
      "measured_at": null,
      "min_score": 23.61062430589122,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 576,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.0119875947582,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 41.20984717192794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "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-2026-07-30": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 4.208937
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 41.34245113044162,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 101,
      "eligibility_flag": true,
      "entry_count": 10,
      "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": [],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:28:45Z",
      "losses": 102,
      "max_score": 52.77796349718378,
      "measured_at": null,
      "min_score": 20.67238336600834,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.021787381488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 38.00705442729109,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "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-2026-07-30": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.80503304728466,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 225,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 268,
      "max_score": 68.24458515523042,
      "measured_at": null,
      "min_score": 16.47955768015164,
      "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": 734,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.1917047351317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.80503304728466,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 241
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash:597ffa78f1056311",
      "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": 3.9126164999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.466137703026426,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 148,
      "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-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 193,
      "max_score": 77.64645353476814,
      "measured_at": null,
      "min_score": 13.591710349239374,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 520,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.9212423268102,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 37.657984375531065,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-flash:2df7e34a8729682d",
      "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": 39.43599888199961,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 149,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 217,
      "max_score": 69.71379024439247,
      "measured_at": null,
      "min_score": 24.5968014699668,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.913477289564,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 36.699332183133805,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "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": 0.0773785,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-30": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 40.145487538652965,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 122,
      "eligibility_flag": true,
      "entry_count": 38,
      "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": "2026-08-05T06:56:02Z",
      "losses": 515,
      "max_score": 50.99483797073365,
      "measured_at": null,
      "min_score": 30.512771329112983,
      "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": 1183,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.6884393870812,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 35.24014138419697,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 546
    },
    {
      "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-2026-07-30": 9
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 6.887694999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.23436045013047,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 153,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:20:31Z",
      "losses": 249,
      "max_score": 55.38133319989706,
      "measured_at": null,
      "min_score": 7.670088947709001,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 600,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.5207692060533,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 33.23436045013047,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:xiaomi-mimo-v2-5:8cd9a74ba97a922e",
      "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": 34.182546170823265,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 224,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 81,
      "max_score": 62.62712426295049,
      "measured_at": null,
      "min_score": 18.9315557741441,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.5608768062757,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 30.393059019139915,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "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": 31.00737150112073,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 180,
      "eligibility_flag": true,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": "2026-08-05T06:56:50Z",
      "losses": 331,
      "max_score": 47.7133517329692,
      "measured_at": null,
      "min_score": 20.20823545772604,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.1841731147556,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 29.98934399569381,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "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": 30.623488700978687,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 153,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 285,
      "max_score": 54.06767438679486,
      "measured_at": null,
      "min_score": 9.407687981142418,
      "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": 632,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9811061129255,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 28.75865346487423,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:openai-gpt-oss-120b:ce0e486e0cf1a6f6",
      "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": 31.297397210158135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 166,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 150,
      "max_score": 66.5532044937622,
      "measured_at": null,
      "min_score": 10.87785451326086,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0840129537567,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 27.827758523316916,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:stepfun-step-3-7-flash:8853b191eba37605",
      "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": 29.291490904881062,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 74,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 255,
      "max_score": 42.140290158190794,
      "measured_at": null,
      "min_score": 15.139582069381618,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 473,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.9007264410452,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 26.044227582746185,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:e1d7a9f9ce945d74",
      "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": 27.441305954041592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 323,
      "eligibility_flag": true,
      "entry_count": 18,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 302,
      "max_score": 39.94026033234647,
      "measured_at": null,
      "min_score": 17.505656326341292,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 783,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.3747431883885,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 23.76486806922119,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 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": 4.1572507100000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.236848647884678,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 167,
      "eligibility_flag": true,
      "entry_count": 18,
      "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": "2026-08-05T05:37:42Z",
      "losses": 276,
      "max_score": 54.719235037247856,
      "measured_at": null,
      "min_score": 16.681032418541818,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.1870983748304,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 23.58780284809997,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-1-flash-lite:9c91a59ff4187199",
      "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": 25.66695092309063,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 128,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 248,
      "max_score": 37.264518924471545,
      "measured_at": null,
      "min_score": 16.44510307833982,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 469,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.1778899472356,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 22.821505172505795,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-sonnet-5:5b20f0cc22749991",
      "capped_draws": 0,
      "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-2026-07-30": 1
        },
        "run_count": 2,
        "token_priced_attempt_count": 3,
        "total": 0.939322
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 52.22657439455518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": 2,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T02:54:54Z",
      "losses": 48,
      "max_score": 52.22657439455518,
      "measured_at": null,
      "min_score": 52.22657439455518,
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.8932580896576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 52.22657439455518,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-2:d0fe34394efdcd81",
      "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": 42.15233778736079,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 21,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "2026-08-05T04:45:51Z",
      "losses": 18,
      "max_score": 42.15233778736079,
      "measured_at": null,
      "min_score": 42.15233778736079,
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.5781271742296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 42.15233778736079,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:mistralai-mistral-medium-3-5:5ebf24b9f35709a6",
      "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": 1.9149450000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.494721172537112,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 19,
      "eligibility_flag": false,
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "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": 257,
      "max_score": 32.00389460443945,
      "measured_at": null,
      "min_score": 14.583182450662427,
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.1309354872262,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "track",
      "score": 17.550366345371355,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "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-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 2000.7576930253301,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "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-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1842.1038472104176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 83.08829242248612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "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-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1821.051700392042,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 80.69363121403609,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.7971143350485,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 79.68193767817715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.3774293727092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 73.2539994315327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "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": "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": 10,
      "max_score": null,
      "measured_at": "2026-08-04T23:08:28Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.4010124412612,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.90936602956313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.61754645133582,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.7809463961355,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.096152664379886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.459772198068393,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.793115128391,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.63498693048245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:20:55Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.8200827421863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.06767438679486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.056388861645896,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 9,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T03:44:03Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.3359090209483,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.00989881361929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 55.00854884223441,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.92650016324,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.61062123130229,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.642442208147656,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 61,
      "draws": 12,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.7883171781857,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.90487405871482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 56.30417418419743,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-pro:e4ede0086e6579b7",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:26Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.4991443772221,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 43.61554479729633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:46Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.9188616540573,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.88844588724325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 46,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:28:59Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.2480909757069,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.77809618811668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.44733143012604,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:31:39Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.9313234311355,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.21919853575708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.80422984590621,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:29:06Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.060421397574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.04185705006656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 52.475044864937615,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-flash:2df7e34a8729682d",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:53:31Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.025506422629,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 33.4805377654376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:e1d7a9f9ce945d74",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:49Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.3506179183505,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.808038955158167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 24,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:42Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.9115333507139,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.898650929285388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 50.78635697673178,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:xiaomi-mimo-v2-5:8cd9a74ba97a922e",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1251.9402308692768,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.9315557741441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stepfun-step-3-7-flash:8853b191eba37605",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:13Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1232.3529714785363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.139582069381618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.406681034422945,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:mistralai-mistral-medium-3-5:5ebf24b9f35709a6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:28Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.277071770066,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 14.583182450662427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1806.880102034298,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.077401945733,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 82.05347374902418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.6468619133602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 75.80812316419362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "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": 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-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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.539453456156,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.99902750726241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.5373124406053,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.21854400867016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.2699961396245,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.40569833085461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-03T11:33:43Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.8610091385813,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 36.83057284966336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 37.89405657207563,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:xiaomi-mimo-v2-5:8cd9a74ba97a922e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0662350094012,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.2390924954411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:deepseek-deepseek-v4-flash:2df7e34a8729682d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 57,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:38:54Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9276220539098,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.386103413880857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.0532689115892,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.96981343482104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "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": 2,
      "distinct_rated_opponents": 16,
      "draws": 55,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:41Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.198212620904,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.67238336600834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 2,
      "distinct_rated_opponents": 10,
      "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-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": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:32Z",
      "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": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.0646270829602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.20823545772604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 68.15840602663853,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:e1d7a9f9ce945d74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 33,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.8422251646493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.505656326341292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.718082484234934,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 2,
      "distinct_rated_opponents": 7,
      "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": "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": 2,
      "max_score": null,
      "measured_at": "2026-08-05T04:06:19Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.565459593351,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.681032418541818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 61.8994692631296,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 57,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:04:56Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.47622141143,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.47955768015164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 37.89405657207563,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 30,
      "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": 2,
      "distinct_rated_opponents": 15,
      "draws": 43,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:14:46Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.9602022628883,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 11.233180622648142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.05265101338746,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:openai-gpt-oss-120b:ce0e486e0cf1a6f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:23:18Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.6077181148798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 10.87785451326086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.812854461075986,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.1191021856469,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 9.407687981142418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 2,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 112,
      "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": 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": "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1886.5839666583847,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 98.38502694069997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 30,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.3473191690596,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 70.49045424400458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.3799977137346,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 57.90485555225239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.7107585816805,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.47594525860797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-sonnet-5:5b20f0cc22749991",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "draws": 70,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T02:54:54Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.8932580896576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.22657439455518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.866089496389785,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 81,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.3839322567405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.35305938673562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-03T14:16:22Z",
      "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": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.952914842092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.72105372304396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 76.23752243246881,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-2:d0fe34394efdcd81",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 21,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:51Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.5781271742296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.15233778736079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash:597ffa78f1056311",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.3273441827764,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.494654124976805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 37.38178527761111,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 24,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:45:57Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.6478351806873,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.83416050750126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 64.63816275334686,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T03:30:50Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7947632570085,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.89608232157542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 2,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "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": 2,
      "distinct_rated_opponents": 12,
      "draws": 20,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-04T23:02:00Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9889629953232,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.228907975804475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 60.8044725589981,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T02:45:49Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.6395980970199,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.960074596473827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 40.76542547285167,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 13,
      "draws": 13,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-03T13:23:14Z",
      "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": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6154597021434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.873359195800802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 76.23752243246881,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 2,
      "distinct_rated_opponents": 13,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 11,
      "max_score": null,
      "measured_at": "2026-08-03T13:23:39Z",
      "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": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.401197179736,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 28.936698930432165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 76.23752243246881,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 29,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 26,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5010278143418,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.836159834589736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.941634169259466,
      "unilateral_faults": 1,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 14,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T13:44:40Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4311400458312,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.677879816109012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 51.15132550669373,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.726476188212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.787023585925473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 17,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1865.823673582791,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 76
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "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": 71,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.096473051806,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 79.47342462976314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.818262520573185,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.1290756470048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 61.74991968984401,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "capped_draws": 0,
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.5726584504935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.01517252922639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 35,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:54:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.201730875163,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.68784123456057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T03:43:28Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.589788462788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.71458862728154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.41912513169022,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 41,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.9585279553617,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.4786439895316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T04:52:16Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.1898264095873,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 35.0157186034202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 40.30945969778741,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:xiaomi-mimo-v2-5:8cd9a74ba97a922e",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 1502.1064415265755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.47394764651104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:50Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.3136234631593,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.466665424316382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:deepseek-deepseek-v4-pro:e4ede0086e6579b7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.1059463245633,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.709033756995762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 12,
      "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": "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9386277122185,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.36619296619383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 65.3927996249965,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:openai-gpt-oss-120b:ce0e486e0cf1a6f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.3413516403082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.716708587278752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 37.61757338116737,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9324472888316,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.596644926517598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-1-flash-lite:9c91a59ff4187199",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.353922850699,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.753586194664617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "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": 4,
      "distinct_rated_opponents": 41,
      "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": "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": 32,
      "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 3.5 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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.65523885426,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.162958277021243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 59.44850826147155,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:e1d7a9f9ce945d74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.5187890361944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.693442822538298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.4364488018932,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.444697310565857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.74828632574542,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-5-flash:597ffa78f1056311",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:04:52Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.573033769448,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 18.838331311955223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T01:11:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.7399927678175,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 17.698293904601133,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.393187298490844,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:50Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.941773211182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 15.142060466906322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 40,
      "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": 2,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "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": 37,
      "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 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.47949608107,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 7.670088947709001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.812854461075986,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2032.5608459804337,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 92.49362898125582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 2007.5728572044336,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 90.25579059650316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 82
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.9846191205747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.20269021147601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:01Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1913.7523653539108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 81.36228215819001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-pro:e4ede0086e6579b7",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.1338387843662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.11107962938964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "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-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:34Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.2371283141379,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 63.86653414034944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.9512272105483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 56.425112707893895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:50Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.20016176997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 53.65215492250481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.3923852536077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.07459338705543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.97128781498596,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:45Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.777615993166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 51.59820019792202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 60.012467245703284,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "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": 2,
      "distinct_rated_opponents": 17,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:06:16Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.477136059127,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 49.08738584494886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 59.14161899550908,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-flash:2df7e34a8729682d",
      "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-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:11:33Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7911348935588,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.95611862982329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:57:20Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.5443530487862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.72757509137996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.9564297708673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.75054191596875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 54,
      "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": 2,
      "distinct_rated_opponents": 27,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:27Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.235945481571,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.773354886116735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 24.966995223862348,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-5-flash:597ffa78f1056311",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:18:45Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9062628518725,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 41.21284375873298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.72324997517388,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 178,
      "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": 8,
      "distinct_rated_opponents": 89,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:49Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.0897511504677,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.20081700407619,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 47.98079888322023,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:stepfun-step-3-7-flash:8853b191eba37605",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:09:34Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0951747410882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.474899556627776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 24.966995223862348,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:e1d7a9f9ce945d74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:09:03Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.4301689763815,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.77351511539399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.164515785801473,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "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": 4,
      "distinct_rated_opponents": 36,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.107361683862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 25.580760401626307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 47.51543856721756,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 70,
      "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": 4,
      "distinct_rated_opponents": 35,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T04:59:54Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1298.0725132394223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.614276485732244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.00101022325288,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:mistralai-mistral-medium-3-5:5ebf24b9f35709a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:56Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.3618154778578,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.886909831937842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.996324165557496,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-1-flash-lite:9c91a59ff4187199",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:53:07Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1245.704202029921,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 16.44510307833982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1935.9305085166034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1880.0797890873182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 94.05837364506577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.949290834117,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 93.83172258846857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:59:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.081054869981,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 85.7032381321606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1786.9238690390182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 84.20334702445369,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.888067823131,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 81.11440057033718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.344551427424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 78.97727049438612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-5-flash:597ffa78f1056311",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1743.6380722729027,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 77.64645353476814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 32,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:42Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1721.3048744665289,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 74.49579059518622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.52149864255874,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 8,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.1996547008405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.24458515523042,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:openai-gpt-oss-120b:ce0e486e0cf1a6f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:32:58Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.439897764506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.5532044937622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.51471483712608,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:xiaomi-mimo-v2-5:8cd9a74ba97a922e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": 28,
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.8776884828033,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 62.62712426295049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 54,
      "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": 2,
      "distinct_rated_opponents": 27,
      "draws": 8,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:20:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.720666438107,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 55.38133319989706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.383827667425074,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "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": 2,
      "distinct_rated_opponents": 13,
      "draws": 3,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:12:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.1147152275953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.719235037247856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 43.405962904620324,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T05:37:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.4632087444165,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.40923463191768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 118,
      "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": 8,
      "distinct_rated_opponents": 59,
      "draws": 7,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-08-05T05:36:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.2972836372262,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.99483797073365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 49.89539365739238,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "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": 4,
      "distinct_rated_opponents": 26,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T05:13:15Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7897534664867,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.7133517329692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 49.068051901535554,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-pro:e4ede0086e6579b7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:08:34Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.5606086737382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 45.6628100593333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:stepfun-step-3-7-flash:8853b191eba37605",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:01:30Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.6267806671017,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 42.140290158190794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 49,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:e1d7a9f9ce945d74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:17:48Z",
      "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": 87,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.7788982716947,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 39.94026033234647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.63737751059915,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-flash:2df7e34a8729682d",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:53:03Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.2737990682394,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.48264176849661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:mistralai-mistral-medium-3-5:5ebf24b9f35709a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:19Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1312.5406298877297,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 32.00389460443945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 45,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-1-flash-lite:9c91a59ff4187199",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:51Z",
      "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": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.513648432589,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 31.215153717922618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 28.824774753010004,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:52:58Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.898542312292,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.65897798586819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.840890457624802,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 2048.6955646228785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.5526124609985,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 92.05790847852163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "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-5.4",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1934.857523033671,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 89.10077480456111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:46Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1808.0596113105762,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 76.38776402098694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "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-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1803.2582355928973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 75.86448374979243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1761.1968899835726,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 71.72102167529864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-flash:2df7e34a8729682d",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.0405753174614,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 69.71379024439247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1713.9112383774284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.9670189086873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:53Z",
      "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": 1633.041024252725,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 58.95884336983468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-pro:e4ede0086e6579b7",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:33Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.3030320455705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.98808344707694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 2,
      "distinct_rated_opponents": 22,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:24:30Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.4714041645075,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.20659865554057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 37.037213613920954,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-5-flash:597ffa78f1056311",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:51:36Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.3036199131727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 54.012833138486045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.759688346625158,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T15:10:28Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.9932384807714,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.77796349718378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.62217943844404,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:11:05Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.486896567064,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 50.4873271878866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.992031574433888,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 47,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T04:24:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 69,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.1110560655984,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 46.508716072525516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 44.46299533862032,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 50,
      "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": 2,
      "distinct_rated_opponents": 25,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-05T04:24:34Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.7354986238543,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 44.28793172321607,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.36952453316905,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "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": 4,
      "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-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": 73,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.9736603594838,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.48268724940904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 43.68183907783984,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 186,
      "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": 8,
      "distinct_rated_opponents": 93,
      "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": 155,
      "max_score": null,
      "measured_at": "2026-08-05T06:56:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.3384324946082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 40.03071689347571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.06107675388781,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-1-flash-lite:9c91a59ff4187199",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:09:18Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.18954362656,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 37.264518924471545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:openai-gpt-oss-120b:ce0e486e0cf1a6f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:39Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.9371892145195,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.24914236422956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.381644683851405,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 53,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:stepfun-step-3-7-flash:8853b191eba37605",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:50:20Z",
      "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": 99,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.418971602498,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.32531783828087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.736938746462222,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 2,
      "distinct_rated_opponents": 26,
      "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": 63,
      "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": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.7720405010791,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.686045371959437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.10955497609672,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:12:54Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.9276344632324,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.48344557638085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:mistralai-mistral-medium-3-5:5ebf24b9f35709a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:22:40Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.3442248132515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.504897803108722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 28.714783570323423,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-fable-5:c5ff581b1631c3b1",
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 2047.0897119000806,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-5:cd449a7bbe670714",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1783.5389156654253,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 68.79504598485697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "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": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.0794210582203,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.46916572650451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.16912059827689,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-8:7b163630bb7a2ff7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:16:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.8005525842925,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 67.02362320555288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 2,
      "distinct_rated_opponents": 24,
      "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": "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": "2026-08-05T03:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.3276397387067,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 66.94474034970983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.00772618643724,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-luna:22b5fdfbba5a7de4",
      "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": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.1650048305432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 52.14226731360425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-terra:8699d609eb9a6d31",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:23:24Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.127256233949,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 48.731858204888034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-4:9f75b771d78a151e",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.560257343934,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 47.28913787090833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:44Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.3131028207222,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 34.36861595666778,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 50.64711429418479,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 78,
      "draws": 83,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:23Z",
      "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": 205,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.627888866674,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 30.512771329112983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 51.770121842860966,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:tencent-hy3-preview:8e4860c5a4f60d63",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:45:25Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.7095025143608,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 29.551395750129856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 25.674278837447822,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:xiaomi-mimo-v2-5:8cd9a74ba97a922e",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8137881433222,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 26.641010675069595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 50,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:53:40Z",
      "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": 1431.2672956941567,
      "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.841215591728457,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 28.524801725696737,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-flash:2df7e34a8729682d",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.422225981586,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 24.5968014699668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-pro:e4ede0086e6579b7",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-pro",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.469355363088,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.61062430589122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5:a35e8773f69fdcf1",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 62,
      "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.6136814138022,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 23.50219767108876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.0733020497882,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:openai-gpt-oss-120b:ce0e486e0cf1a6f6",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.0939080345697,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.090076092259295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.059739949501434,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 2,
      "distinct_rated_opponents": 26,
      "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": "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": 27,
      "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": "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.1744868927296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 22.034961332646205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 35.491466493865985,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:e1d7a9f9ce945d74",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 54,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.32775976306,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.92692217247133,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.32197342861184,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-1-flash-lite:9c91a59ff4187199",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.128132796408,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.65639270005456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 25.674278837447822,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stepfun-step-3-7-flash:8853b191eba37605",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.0097337160018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 21.377364901924253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.21770585958794,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-sol:f9b60ff9ef1cd56e",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:22:45Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.8902558829477,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 20.34202322749009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5064376721202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 19.05599677831604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.059739949501434,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash:597ffa78f1056311",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.7791209706893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260807-e64919171e70",
      "row_kind": "game",
      "score": 13.591710349239374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "latest_effective_request_cohort_equal_mean_mixed_variants_v13",
      "snapshot_id": "20260807_123334",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.003433595313624,
      "unilateral_faults": 0,
      "wins": 0
    }
  ],
  "schema_version": 10,
  "snapshot_id": "20260807_123334",
  "suite_line_id": "gamebench2",
  "suite_version": "2-known8-r3"
}