{
  "benchmark_line": "gamebench2",
  "comparability_tuples": [
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "balanced",
      "results_cut_id": "20260727_194501",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": "20260727_194501",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": "20260727_194501",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": "20260727_194501",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": "20260727_194501",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_kind": "overall"
    }
  ],
  "generated_at": "2026-07-27T19:45:01Z",
  "public_release_id": "gb2-20260727-4d94e2ae1be2",
  "results_cut_id": "gb2-20260727-4d94e2ae1be2",
  "rows": [
    {
      "admitted_plugins": 8,
      "attempted_matches": 466,
      "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-2026-07-25": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.66097
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.47120747309498,
      "contributing_entrants": null,
      "distinct_rated_opponents": 233,
      "draws": 66,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:20:16Z",
      "losses": 80,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 61.39391405879897,
      "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": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1732.6539292122177,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 83.47120747309498,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 320
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 520,
      "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": 1.320515,
        "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": 77.51610158816355,
      "contributing_entrants": null,
      "distinct_rated_opponents": 260,
      "draws": 40,
      "entry_count": 13,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:19:34Z",
      "losses": 100,
      "max_score": 99.01750849232472,
      "measured_at": null,
      "min_score": 63.475663086016624,
      "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": 520,
      "rating_method": "sequential_elo",
      "raw_elo": 1759.0864439224283,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 73.59490781264122,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 486,
      "capped_draws": 22,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.140645
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 71.87937601763771,
      "contributing_entrants": null,
      "distinct_rated_opponents": 243,
      "draws": 101,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:53:35Z",
      "losses": 87,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 38.82631568621353,
      "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": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1707.4052727023304,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 71.87937601763771,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 298
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 732,
      "capped_draws": 7,
      "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": 0.4461796875,
        "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": 72.42802335561073,
      "contributing_entrants": null,
      "distinct_rated_opponents": 366,
      "draws": 103,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:50Z",
      "losses": 181,
      "max_score": 92.5436481576926,
      "measured_at": null,
      "min_score": 43.13791710250739,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.6100169154984,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 70.0500817123776,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 448
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 434,
      "capped_draws": 30,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.15184887212625,
      "contributing_entrants": null,
      "distinct_rated_opponents": 217,
      "draws": 98,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:29:49Z",
      "losses": 94,
      "max_score": 88.02796582947613,
      "measured_at": null,
      "min_score": 30.921753926830576,
      "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": 433,
      "rating_method": "sequential_elo",
      "raw_elo": 1680.483773314538,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 65.91430169096594,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 241
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 490,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 80.47395
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 65.28432384240854,
      "contributing_entrants": null,
      "distinct_rated_opponents": 245,
      "draws": 59,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:17:28Z",
      "losses": 138,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 15.99986870925893,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.6753266447145,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 65.28432384240854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7,
      "attempted_matches": 396,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0372
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 65.57074160938022,
      "contributing_entrants": null,
      "distinct_rated_opponents": 198,
      "draws": 62,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:59Z",
      "losses": 108,
      "max_score": 75.98738578456185,
      "measured_at": null,
      "min_score": 50.169539127004974,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.01775040059,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 63.41793679949243,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": 1528,
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12366493333333332,
        "mean": 0.09185773333333332,
        "median": 0.09170913333333332,
        "min": 0.04980146666666666,
        "recorded_attempt_count": 39,
        "run_count": 24,
        "total": 2.2045855999999997
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 61.02342972194618,
      "contributing_entrants": null,
      "distinct_rated_opponents": 763,
      "draws": 354,
      "entry_count": 23,
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.4166666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "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": "2026-07-27T16:02:13Z",
      "losses": 419,
      "max_score": 85.57962471129208,
      "measured_at": null,
      "min_score": 38.01628425017713,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.9583333333333334,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1528,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.304606454339,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 13,
      "repaired_rate": 0.5416666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 60.377588250409744,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 755
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 684,
      "capped_draws": 48,
      "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": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570124999999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 62.167829720841986,
      "contributing_entrants": null,
      "distinct_rated_opponents": 342,
      "draws": 161,
      "entry_count": 13,
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 170,
      "max_score": 83.50388880910803,
      "measured_at": null,
      "min_score": 48.01330799880638,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.8125,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 684,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.2407752912268,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 59.0230365495569,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8,
      "attempted_matches": 452,
      "capped_draws": 7,
      "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": 0.366615,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 4.11992
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 59.534531948954026,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 103,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:58:56Z",
      "losses": 126,
      "max_score": 76.15659509023824,
      "measured_at": null,
      "min_score": 34.29690331835047,
      "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": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.2424875928227,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 57.80705078732788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8,
      "attempted_matches": 496,
      "capped_draws": 22,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.13752,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.32801249999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.919234658332655,
      "contributing_entrants": null,
      "distinct_rated_opponents": 248,
      "draws": 97,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:55:10Z",
      "losses": 169,
      "max_score": 72.0322843616957,
      "measured_at": null,
      "min_score": 43.85247714738262,
      "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": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.7047709144026,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 54.919234658332655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 542,
      "capped_draws": 55,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.1598575,
        "mean": 0.093565,
        "median": 0.07461,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7485199999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.995707750614955,
      "contributing_entrants": null,
      "distinct_rated_opponents": 271,
      "draws": 201,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:13Z",
      "losses": 119,
      "max_score": 92.11822076992448,
      "measured_at": null,
      "min_score": 29.006597636421393,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.1429759628736,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 52.995707750614955,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 460,
      "capped_draws": 57,
      "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": 52.23257256057504,
      "contributing_entrants": null,
      "distinct_rated_opponents": 229,
      "draws": 163,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 112,
      "max_score": 89.30637072728769,
      "measured_at": null,
      "min_score": 20.44814764085012,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 458,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.8911595246293,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 52.23257256057504,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 472,
      "capped_draws": 7,
      "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-2026-07-25": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 28.806541000000003
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 51.9216378429439,
      "contributing_entrants": null,
      "distinct_rated_opponents": 236,
      "draws": 132,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:56:30Z",
      "losses": 155,
      "max_score": 76.4748305783871,
      "measured_at": null,
      "min_score": 28.146372762679754,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.1347318400751,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 50.415055892633696,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16,
      "attempted_matches": 644,
      "capped_draws": 47,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0820533,
        "mean": 0.0699502125,
        "median": 0.06609614999999999,
        "min": 0.0587988,
        "recorded_attempt_count": 17,
        "run_count": 16,
        "total": 1.1192034
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 50.22774359214498,
      "contributing_entrants": null,
      "distinct_rated_opponents": 322,
      "draws": 305,
      "entry_count": 27,
      "failed_game_aliases": [],
      "first_pass_admitted": 15,
      "first_pass_rate": 0.9375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:01:47Z",
      "losses": 257,
      "max_score": 67.27022799576758,
      "measured_at": null,
      "min_score": 26.07854941714752,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 644,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.8511208571324,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 50.22774359214498,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 444
    },
    {
      "admitted_plugins": 20,
      "attempted_matches": 716,
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.1445437333333333,
        "mean": 0.08818255,
        "median": 0.07401653333333333,
        "min": 0.052337466666666665,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 2.1163812
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 51.68224842902943,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 261,
      "entry_count": 40,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 12,
      "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
      },
      "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": "2026-07-27T15:57:47Z",
      "losses": 479,
      "max_score": 64.73590439615545,
      "measured_at": null,
      "min_score": 22.82665639057853,
      "model_code_failure_rate": 0.16666666666666666,
      "model_code_failures": 4,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.8333333333333334,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 716,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.1231601642353,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 8,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 49.37943174643163,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 698
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1047,
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "max": 0.25698975,
        "mean": 0.172479834375,
        "median": 0.166217925,
        "min": 0.10864875,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 2.75967735
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 49.33456114316592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 523,
      "draws": 389,
      "entry_count": 16,
      "failed_game_aliases": [],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 268,
      "max_score": 79.84257508312278,
      "measured_at": null,
      "min_score": 22.04868244275925,
      "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": 1046,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.7511937613583,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 49.33456114316592,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 389
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 422,
      "capped_draws": 6,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.44989
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.53327801033048,
      "contributing_entrants": null,
      "distinct_rated_opponents": 211,
      "draws": 59,
      "entry_count": 7,
      "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
      },
      "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": "2026-07-27T11:53:30Z",
      "losses": 123,
      "max_score": 50.53327801033048,
      "measured_at": null,
      "min_score": 50.53327801033048,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.7804147256502,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 48.87418004544679,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 484,
      "capped_draws": 49,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.989149999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.48149951346338,
      "contributing_entrants": null,
      "distinct_rated_opponents": 242,
      "draws": 181,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:20Z",
      "losses": 131,
      "max_score": 91.83061764137966,
      "measured_at": null,
      "min_score": 25.189567064800336,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0495869021083,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 48.48149951346338,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 454,
      "capped_draws": 65,
      "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": 0.442856875,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.542855
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.09744784101551,
      "contributing_entrants": null,
      "distinct_rated_opponents": 227,
      "draws": 153,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:56Z",
      "losses": 144,
      "max_score": 65.58294385391025,
      "measured_at": null,
      "min_score": 27.3472600456232,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.8784219094462,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 48.09744784101551,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 18,
      "attempted_matches": 725,
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 18,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.9392418,
        "mean": 0.7382814249999998,
        "median": 0.7264120999999999,
        "min": 0.4980382,
        "recorded_attempt_count": 48,
        "run_count": 23,
        "total": 16.779512399999994
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": 50.681284389884866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 363,
      "draws": 412,
      "entry_count": 36,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:54:18Z",
      "losses": 407,
      "max_score": 53.42069139868415,
      "measured_at": null,
      "min_score": 46.17117874326892,
      "model_code_failure_rate": 0.21739130434782608,
      "model_code_failures": 5,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.782608695652174,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 725,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.933390281058,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": 18,
      "repaired_rate": 0.782608695652174,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 47.668751755366614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 528
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 500,
      "capped_draws": 56,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.97393
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.14570999192436,
      "contributing_entrants": null,
      "distinct_rated_opponents": 250,
      "draws": 174,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:35Z",
      "losses": 146,
      "max_score": 59.15070675443215,
      "measured_at": null,
      "min_score": 35.18281284883366,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 500,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.5505511671608,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 47.14570999192436,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 462,
      "capped_draws": 72,
      "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": 0.046574,
        "mean": 0.036155625,
        "median": 0.035338,
        "min": 0.025803,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 0.315048
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 48.32188705528165,
      "contributing_entrants": null,
      "distinct_rated_opponents": 231,
      "draws": 206,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T16:02:31Z",
      "losses": 127,
      "max_score": 65.24239570415726,
      "measured_at": null,
      "min_score": 30.356162068590265,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.046193867148,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.919757117419735,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 768,
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 7,
        "cost_basis_counts": {
          "local_standard_estimate": 15
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.5164726249999998,
        "mean": 1.0182428035714286,
        "median": 0.9670455,
        "min": 0.8356068750000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 15
        },
        "run_count": 12,
        "token_priced_attempt_count": 15,
        "total": 12.214044
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 46.85603201539517,
      "contributing_entrants": null,
      "distinct_rated_opponents": 384,
      "draws": 207,
      "entry_count": 12,
      "failed_game_aliases": [],
      "first_pass_admitted": 10,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 271,
      "max_score": 66.08919562986975,
      "measured_at": null,
      "min_score": 28.93961926553232,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 768,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.0200419973128,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.85603201539517,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 636,
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "max": 0.116343,
        "mean": 0.07787519999999999,
        "median": 0.0843883,
        "min": 0.041110400000000005,
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 1.2460032
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 46.61900356772293,
      "contributing_entrants": null,
      "distinct_rated_opponents": 318,
      "draws": 326,
      "entry_count": 28,
      "failed_game_aliases": [],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 258,
      "max_score": 76.23053193535173,
      "measured_at": null,
      "min_score": 20.684453538846107,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.8256477101834,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": 11,
      "repaired_rate": 0.6875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.61900356772293,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 406
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 448,
      "capped_draws": 16,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.262825
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.38943024530096,
      "contributing_entrants": null,
      "distinct_rated_opponents": 224,
      "draws": 112,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:41Z",
      "losses": 147,
      "max_score": 62.93013963759991,
      "measured_at": null,
      "min_score": 28.832423610551896,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.571681633783,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.83355042960994,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 528,
      "capped_draws": 30,
      "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": 0.121464375,
        "median": 0.124865,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.0694849999999998
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 47.16916339303791,
      "contributing_entrants": null,
      "distinct_rated_opponents": 264,
      "draws": 149,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:56:29Z",
      "losses": 177,
      "max_score": 59.90860829604776,
      "measured_at": null,
      "min_score": 32.11930845299747,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 528,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.1348386309048,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.8004814112764,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 430,
      "capped_draws": 63,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.26724769418371,
      "contributing_entrants": null,
      "distinct_rated_opponents": 215,
      "draws": 166,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 121,
      "max_score": 77.20302117516688,
      "measured_at": null,
      "min_score": 26.35973023478462,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 430,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.898443627913,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.26724769418371,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 626,
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4567,
        "mean": 0.3660333333333334,
        "median": 0.355077,
        "min": 0.234622,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-25": 8
        },
        "run_count": 10,
        "token_priced_attempt_count": 10,
        "total": 3.5443079999999996
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 45.05500396335153,
      "contributing_entrants": null,
      "distinct_rated_opponents": 313,
      "draws": 195,
      "entry_count": 10,
      "failed_game_aliases": [],
      "first_pass_admitted": 10,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 18,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:30Z",
      "losses": 219,
      "max_score": 59.06172320072071,
      "measured_at": null,
      "min_score": 31.45351907819096,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7968903732362,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.05500396335153,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 212
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 446,
      "capped_draws": 73,
      "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": 0.0216425,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.0701532764951,
      "contributing_entrants": null,
      "distinct_rated_opponents": 223,
      "draws": 163,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:01:47Z",
      "losses": 142,
      "max_score": 80.99600365638999,
      "measured_at": null,
      "min_score": 29.95785357363107,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 446,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.7971729058434,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 44.557587685019186,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 782,
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.00223773125,
        "median": 0.00220356,
        "min": 0.00093502,
        "recorded_attempt_count": 23,
        "run_count": 14,
        "total": 0.030659259999999997
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 45.96433865838611,
      "contributing_entrants": null,
      "distinct_rated_opponents": 391,
      "draws": 255,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.42857142857142855,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:28Z",
      "losses": 267,
      "max_score": 58.47714496936588,
      "measured_at": null,
      "min_score": 23.58388507203711,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 782,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6217233416023,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.42857142857142855,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 44.226677896070974,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 260
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 384,
      "capped_draws": 66,
      "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": 45.85533896437726,
      "contributing_entrants": null,
      "distinct_rated_opponents": 192,
      "draws": 90,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:53:51Z",
      "losses": 144,
      "max_score": 76.6585459712308,
      "measured_at": null,
      "min_score": 23.27152769675579,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 384,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.248635605296,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.67320125602332,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 534,
      "capped_draws": 86,
      "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-2026-07-25": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063374999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.74920947025871,
      "contributing_entrants": null,
      "distinct_rated_opponents": 266,
      "draws": 235,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T16:02:00Z",
      "losses": 162,
      "max_score": 56.98896235225361,
      "measured_at": null,
      "min_score": 27.543654388822937,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 534,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.3895713118704,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.47976243302143,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 444,
      "capped_draws": 53,
      "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": 0.158095,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.33952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.35164383250624,
      "contributing_entrants": null,
      "distinct_rated_opponents": 221,
      "draws": 189,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T16:02:13Z",
      "losses": 121,
      "max_score": 52.41858338546655,
      "measured_at": null,
      "min_score": 30.06424289135372,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 444,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9457841650956,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.35164383250624,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8,
      "attempted_matches": 294,
      "capped_draws": 35,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.454645,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.15278157179898,
      "contributing_entrants": null,
      "distinct_rated_opponents": 147,
      "draws": 168,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:45Z",
      "losses": 174,
      "max_score": 62.786908880400794,
      "measured_at": null,
      "min_score": 24.57930679395035,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 293,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.4392846428914,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.15278157179898,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 183
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 508,
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.3926418,
        "mean": 0.31750829999999997,
        "median": 0.32150055,
        "min": 0.2298153,
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 5.0801327999999994
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.64692033959544,
      "contributing_entrants": null,
      "distinct_rated_opponents": 254,
      "draws": 360,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-05"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.0625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:57Z",
      "losses": 204,
      "max_score": 68.20962819187783,
      "measured_at": null,
      "min_score": 21.27615981022488,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.9375,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 508,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.6308672353125,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 14,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.96434936980171,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 412,
      "capped_draws": 67,
      "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": 0.21477375,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.07706583204088,
      "contributing_entrants": null,
      "distinct_rated_opponents": 206,
      "draws": 143,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 136,
      "max_score": 57.29494455453205,
      "measured_at": null,
      "min_score": 26.83423634499792,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.1400277773191,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.66276865859234,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": 1090,
      "capped_draws": 159,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.004834030033333333,
        "mean": 0.0027724950333333333,
        "median": 0.0022439992166666664,
        "min": 0.00169122,
        "recorded_attempt_count": 35,
        "run_count": 24,
        "total": 0.06653988079999999
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 45.06881836311115,
      "contributing_entrants": null,
      "distinct_rated_opponents": 545,
      "draws": 334,
      "entry_count": 17,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 412,
      "max_score": 47.38658897369575,
      "measured_at": null,
      "min_score": 40.46122645082023,
      "model_code_failure_rate": 0.2916666666666667,
      "model_code_failures": 7,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7083333333333334,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1090,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.314911503901,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333337,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.34619909670711,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 344
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 454,
      "capped_draws": 110,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.48343610226164,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 244,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:24Z",
      "losses": 99,
      "max_score": 56.42732881438667,
      "measured_at": null,
      "min_score": 27.049679476012503,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.5841541841166,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.08862885535952,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 366,
      "capped_draws": 45,
      "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": 0.03731,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.151619765977394,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 99,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:52:44Z",
      "losses": 132,
      "max_score": 57.32634647961873,
      "measured_at": null,
      "min_score": 27.82583876113024,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.6255950166408,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.087711891446865,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15,
      "attempted_matches": 961,
      "capped_draws": 148,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.38568888333333334,
        "mean": 0.29249454166666666,
        "median": 0.2834616125,
        "min": 0.2238526,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 25
        },
        "run_count": 17,
        "token_priced_attempt_count": 25,
        "total": 5.07700365
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": 42.36624656479914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 481,
      "draws": 320,
      "entry_count": 15,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.5882352941176471,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 9,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:49Z",
      "losses": 340,
      "max_score": 42.36624656479914,
      "measured_at": null,
      "min_score": 42.36624656479914,
      "model_code_failure_rate": 0.1176470588235294,
      "model_code_failures": 2,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.8823529411764706,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 961,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9236744831069,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.29411764705882354,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.0610994492053,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 301
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 222,
      "capped_draws": 27,
      "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": 0.121855,
        "mean": 0.09110296875,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.7288237500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.85260378513726,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 162,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:57Z",
      "losses": 137,
      "max_score": 67.28650528900698,
      "measured_at": null,
      "min_score": 29.188858982099404,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.5186198209324,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.47850789231176,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 408,
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.02955606902857143,
        "median": 0.0063034062,
        "min": 0.0057139812,
        "recorded_attempt_count": 10,
        "run_count": 7,
        "total": 0.2068924832
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 41.81697003012698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 204,
      "draws": 113,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 151,
      "max_score": 67.54305795364324,
      "measured_at": null,
      "min_score": 28.65315269754207,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.7333897226706,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.23609863849646,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6,
      "attempted_matches": 168,
      "capped_draws": 27,
      "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": 0.0276132876,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.10999191243746,
      "contributing_entrants": null,
      "distinct_rated_opponents": 84,
      "draws": 86,
      "entry_count": 11,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:26:15Z",
      "losses": 156,
      "max_score": 61.78504534403884,
      "measured_at": null,
      "min_score": 25.340296080038364,
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.9489718796042,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.11836794956651,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0148808,
        "mean": 0.0114004875,
        "median": 0.01124825,
        "min": 0.00845595,
        "recorded_attempt_count": 23,
        "run_count": 16,
        "total": 0.1824078
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 39.95432300929791,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 228,
      "entry_count": 15,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:18:59Z",
      "losses": 202,
      "max_score": 65.72298874215366,
      "measured_at": null,
      "min_score": 14.65937731419278,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.2283589294589,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 39.3148475023505,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": 1351,
      "capped_draws": 173,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 26
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.29749325,
        "mean": 0.24155631250000004,
        "median": 0.24021375,
        "min": 0.17873725,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 5.7973514999999995
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 39.72454249564468,
      "contributing_entrants": null,
      "distinct_rated_opponents": 676,
      "draws": 496,
      "entry_count": 23,
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 22,
      "first_pass_rate": 0.9166666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 448,
      "max_score": 48.22471380142931,
      "measured_at": null,
      "min_score": 26.657621512898544,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 0.9583333333333334,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1351,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8797990384317,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 39.304117798140794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 407
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 474,
      "capped_draws": 87,
      "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": 0.015562441375,
        "median": 0.0131167185,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.124499531
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.04782157796235,
      "contributing_entrants": null,
      "distinct_rated_opponents": 236,
      "draws": 159,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:14Z",
      "losses": 161,
      "max_score": 76.1429991599217,
      "measured_at": null,
      "min_score": 20.61584059577335,
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.8800202747846,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.73297991531701,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "max": 0.058529250000000005,
        "mean": 0.03888066562499999,
        "median": 0.038104875,
        "min": 0.029012250000000003,
        "recorded_attempt_count": 20,
        "run_count": 16,
        "total": 0.6220906500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.663748074092574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 272,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:19:02Z",
      "losses": 208,
      "max_score": 58.83351636895526,
      "measured_at": null,
      "min_score": 24.01162765730244,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.085554722274,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.663748074092574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 404,
      "capped_draws": 22,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 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": 41.537281009126794,
      "contributing_entrants": null,
      "distinct_rated_opponents": 202,
      "draws": 105,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:23Z",
      "losses": 143,
      "max_score": 53.01828026826074,
      "measured_at": null,
      "min_score": 27.705611244015376,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.1982821115696,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.654795540982754,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 200,
      "capped_draws": 25,
      "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": 0.4890770625000001,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.912616499999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.533353004955416,
      "contributing_entrants": null,
      "distinct_rated_opponents": 100,
      "draws": 113,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:55:09Z",
      "losses": 132,
      "max_score": 68.09932142027597,
      "measured_at": null,
      "min_score": 18.014153696699164,
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.17126791969,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.6511401212143,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7,
      "attempted_matches": 426,
      "capped_draws": 53,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.624428
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.86834859384712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 213,
      "draws": 144,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:40Z",
      "losses": 134,
      "max_score": 50.22582047612717,
      "measured_at": null,
      "min_score": 27.035172472656587,
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 426,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.663964902354,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.55939935050291,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 224,
      "capped_draws": 32,
      "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": 0.43500895999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.327281492102216,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 146,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:30Z",
      "losses": 122,
      "max_score": 59.51052506806163,
      "measured_at": null,
      "min_score": 26.919709973327855,
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.2485760943189,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.45936897003059,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19,
      "attempted_matches": 1197,
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 57
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.25293804044999996,
        "mean": 0.19953128278324997,
        "median": 0.20662718916666667,
        "min": 0.13279406625,
        "recorded_attempt_count": 57,
        "run_count": 27,
        "total": 5.24138213703
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": 41.614377784832975,
      "contributing_entrants": null,
      "distinct_rated_opponents": 599,
      "draws": 428,
      "entry_count": 19,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.037037037037037035,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:55:02Z",
      "losses": 392,
      "max_score": 57.31929094075836,
      "measured_at": null,
      "min_score": 29.39591170776535,
      "model_code_failure_rate": 0.2962962962962963,
      "model_code_failures": 8,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 0.7037037037037037,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1197,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.36299190223,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 18,
      "repaired_rate": 0.6666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.11455597169624,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 377
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 314,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 13
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.136952,
        "mean": 0.07424775,
        "median": 0.070604,
        "min": 0.041758,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13
        },
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.593982
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.5280618812843,
      "contributing_entrants": null,
      "distinct_rated_opponents": 156,
      "draws": 103,
      "entry_count": 12,
      "failed_game_aliases": [],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:23Z",
      "losses": 102,
      "max_score": 86.61766309589059,
      "measured_at": null,
      "min_score": 18.13272808568275,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.5044579634953,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.5280618812843,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "max": 0.04815395,
        "mean": 0.0408814375,
        "median": 0.040641,
        "min": 0.0341807,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.654103
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.20768319617477,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 232,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T04:34:09Z",
      "losses": 230,
      "max_score": 54.39524382491415,
      "measured_at": null,
      "min_score": 25.068514273806112,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.0836370972834,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 16,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.20768319617477,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.04649778,
        "mean": 0.039593841,
        "median": 0.039509778,
        "min": 0.030762138,
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 0.633501456
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 39.88431631802561,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 126,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:11:55Z",
      "losses": 198,
      "max_score": 51.27239116238635,
      "measured_at": null,
      "min_score": 19.49239768223592,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.0975137826113,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.1165385675198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 252,
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.4852846
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.88241645259816,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 183,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 168,
      "max_score": 53.736898671389504,
      "measured_at": null,
      "min_score": 26.15877822959248,
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.093283579921,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 36.88241645259816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 622,
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.71686460002738,
      "contributing_entrants": null,
      "distinct_rated_opponents": 311,
      "draws": 422,
      "entry_count": 39,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:31Z",
      "losses": 510,
      "max_score": 49.6663365380428,
      "measured_at": null,
      "min_score": 20.918128242024164,
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 622,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.3774251826492,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 36.71686460002738,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 414
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 434,
      "capped_draws": 80,
      "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": 39.08501586962297,
      "contributing_entrants": null,
      "distinct_rated_opponents": 217,
      "draws": 200,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:31Z",
      "losses": 119,
      "max_score": 72.6465473220185,
      "measured_at": null,
      "min_score": 26.272777344588157,
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5637183271122,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 36.37270568635381,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 184,
      "capped_draws": 2,
      "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": 1.2830031540000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.34111208929003,
      "contributing_entrants": null,
      "distinct_rated_opponents": 92,
      "draws": 97,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:21Z",
      "losses": 140,
      "max_score": 48.456236804374136,
      "measured_at": null,
      "min_score": 23.668410863923103,
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.2527923894484,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.680425213671555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 914,
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.014209038,
        "mean": 0.0093957345,
        "median": 0.009312405,
        "min": 0.004429524000000001,
        "recorded_attempt_count": 25,
        "run_count": 16,
        "total": 0.150331752
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.70527307375653,
      "contributing_entrants": null,
      "distinct_rated_opponents": 457,
      "draws": 314,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:46Z",
      "losses": 351,
      "max_score": 52.54958566492595,
      "measured_at": null,
      "min_score": 23.22225700698019,
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 914,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.8553869792495,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.50017326121874,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 296,
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.0260953,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.51873040253819,
      "contributing_entrants": null,
      "distinct_rated_opponents": 148,
      "draws": 83,
      "entry_count": 7,
      "failed_game_aliases": [
        "GB2-02"
      ],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:43Z",
      "losses": 123,
      "max_score": 49.72936122718848,
      "measured_at": null,
      "min_score": 19.57553453515884,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.875,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.4001767574143,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.31975511978292,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 700,
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 26
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.015971877,
        "mean": 0.00979196948,
        "median": 0.009500477,
        "min": 0.003562685,
        "recorded_attempt_count": 26,
        "run_count": 15,
        "total": 0.14255357568
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 37.746016066935304,
      "contributing_entrants": null,
      "distinct_rated_opponents": 350,
      "draws": 182,
      "entry_count": 11,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:47:12Z",
      "losses": 312,
      "max_score": 49.93322035186378,
      "measured_at": null,
      "min_score": 29.692155158998496,
      "model_code_failure_rate": 0.26666666666666666,
      "model_code_failures": 4,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.7333333333333333,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.8639466038817,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.4,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.9298304006065,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 960,
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "max": 0.03261155,
        "mean": 0.02559155625,
        "median": 0.02516155,
        "min": 0.017927,
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 0.4094649
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.76846744526695,
      "contributing_entrants": null,
      "distinct_rated_opponents": 478,
      "draws": 350,
      "entry_count": 15,
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.0625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:05Z",
      "losses": 341,
      "max_score": 49.5426251223461,
      "measured_at": null,
      "min_score": 17.769416290858764,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.0673219253688,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 15,
      "repaired_rate": 0.9375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.76846744526695,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 263
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 750,
      "capped_draws": 72,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.053540475,
        "mean": 0.026315053125,
        "median": 0.024512850000000003,
        "min": 0.012912625,
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 0.4210408500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.93587026592818,
      "contributing_entrants": null,
      "distinct_rated_opponents": 375,
      "draws": 252,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 307,
      "max_score": 50.09192000149523,
      "measured_at": null,
      "min_score": 26.63272439732407,
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.7292460924964,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.37270034463752,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 1564,
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 29
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.021615250000000003,
        "mean": 0.017288937500000004,
        "median": 0.01830825,
        "min": 0.01259225,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 29
        },
        "run_count": 24,
        "token_priced_attempt_count": 29,
        "total": 0.4149345
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 33.80666922295059,
      "contributing_entrants": null,
      "distinct_rated_opponents": 780,
      "draws": 631,
      "entry_count": 24,
      "failed_game_aliases": [],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.7916666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 549,
      "max_score": 50.38643236051798,
      "measured_at": null,
      "min_score": 21.486420364689437,
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1564,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.7509540537976,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333337,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.80666922295059,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 384
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 716,
      "capped_draws": 35,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.07934969,
        "mean": 0.053583788125,
        "median": 0.0553142075,
        "min": 0.02549349,
        "recorded_attempt_count": 37,
        "run_count": 16,
        "total": 0.8573406100000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.83992960363705,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 188,
      "entry_count": 11,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-06",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:14Z",
      "losses": 291,
      "max_score": 53.355787870899725,
      "measured_at": null,
      "min_score": 30.50702629256417,
      "model_code_failure_rate": 0.3125,
      "model_code_failures": 5,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.6875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 716,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.688276622674,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 11,
      "repaired_rate": 0.6875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.54570838202333,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 380,
      "capped_draws": 67,
      "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": 0.001130258,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.01972526
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.40505179177216,
      "contributing_entrants": null,
      "distinct_rated_opponents": 190,
      "draws": 180,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:23Z",
      "losses": 116,
      "max_score": 39.3681250027,
      "measured_at": null,
      "min_score": 29.486147225977007,
      "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": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.5856012817162,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 32.308304150876324,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 1508,
      "capped_draws": 148,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 49
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 7,
        "max": 0.036200562500000005,
        "mean": 0.024352715625,
        "median": 0.025206018750000003,
        "min": 0.016582062499999998,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 49
        },
        "run_count": 32,
        "token_priced_attempt_count": 49,
        "total": 0.7792869
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 33.85869493427405,
      "contributing_entrants": null,
      "distinct_rated_opponents": 755,
      "draws": 415,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.40625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:57Z",
      "losses": 675,
      "max_score": 55.56433079370909,
      "measured_at": null,
      "min_score": 19.10293660731239,
      "model_code_failure_rate": 0.21875,
      "model_code_failures": 7,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.78125,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1508,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.445144486349,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.832278224424897,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 418
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 132,
      "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": 36.401921714481134,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 47,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:51:07Z",
      "losses": 110,
      "max_score": 43.730006809943795,
      "measured_at": null,
      "min_score": 29.16636028907312,
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.1635317602309,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.64935029638511,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 22
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.00596013,
        "mean": 0.0023956312500000004,
        "median": 0.00186283,
        "min": 0.00105702,
        "recorded_attempt_count": 22,
        "run_count": 14,
        "total": 0.03542156
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 33.56861302601268,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 223,
      "entry_count": 11,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T04:30:24Z",
      "losses": 140,
      "max_score": 40.239662184794696,
      "measured_at": null,
      "min_score": 26.087039515938308,
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.0114607809107,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.604546286081508,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8,
      "attempted_matches": 324,
      "capped_draws": 45,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0032939400000000004,
        "mean": 0.0016413085,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.591515338160217,
      "contributing_entrants": null,
      "distinct_rated_opponents": 162,
      "draws": 121,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 123,
      "max_score": 49.8631353550523,
      "measured_at": null,
      "min_score": 11.042241208882738,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.316982892477,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.591515338160217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6,
      "attempted_matches": 366,
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00391754,
        "mean": 0.0023617857142857143,
        "median": 0.00186618,
        "min": 0.00144036,
        "recorded_attempt_count": 8,
        "run_count": 7,
        "total": 0.0165325
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 32.14193352522236,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 106,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 152,
      "max_score": 44.39699646208931,
      "measured_at": null,
      "min_score": 22.18853644184757,
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.1527338375363,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.926822455599037,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 1646,
      "capped_draws": 263,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 56
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 7,
        "max": 0.013223525,
        "mean": 0.0089983359375,
        "median": 0.00845865,
        "min": 0.0058062875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 56
        },
        "run_count": 32,
        "token_priced_attempt_count": 56,
        "total": 0.28794675000000003
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 32.52979168045882,
      "contributing_entrants": null,
      "distinct_rated_opponents": 823,
      "draws": 638,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 589,
      "max_score": 36.65857398163143,
      "measured_at": null,
      "min_score": 28.45383607650836,
      "model_code_failure_rate": 0.21875,
      "model_code_failures": 7,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.78125,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1646,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.5660707930397,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 15,
      "repaired_rate": 0.46875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.58290880274737,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 419
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 1246,
      "capped_draws": 189,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0027823742,
        "mean": 0.0022230800541666665,
        "median": 0.002112839,
        "min": 0.001825724,
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 0.0533539213
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 32.04826272157318,
      "contributing_entrants": null,
      "distinct_rated_opponents": 623,
      "draws": 506,
      "entry_count": 19,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5833333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 455,
      "max_score": 38.39386082118144,
      "measured_at": null,
      "min_score": 25.35335800760461,
      "model_code_failure_rate": 0.20833333333333337,
      "model_code_failures": 5,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.7916666666666666,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1246,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.778886436927,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333337,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.23013467663233,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 285
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 180,
      "capped_draws": 25,
      "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": 32.46627609691285,
      "contributing_entrants": null,
      "distinct_rated_opponents": 90,
      "draws": 112,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:12Z",
      "losses": 144,
      "max_score": 43.2871495944819,
      "measured_at": null,
      "min_score": 19.585628377608835,
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.3850372603245,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.213274292737445,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5,
      "attempted_matches": 202,
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.01660212,
        "mean": 0.00855959175,
        "median": 0.005979701,
        "min": 0.00271606,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.068476734
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.71387606868023,
      "contributing_entrants": null,
      "distinct_rated_opponents": 101,
      "draws": 150,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:46:17Z",
      "losses": 104,
      "max_score": 61.50686447534633,
      "measured_at": null,
      "min_score": 18.82577587485795,
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.826713868567,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 29.976345822769016,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5,
      "attempted_matches": 302,
      "capped_draws": 56,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0445032,
        "mean": 0.03204184375,
        "median": 0.0312573,
        "min": 0.0200767,
        "recorded_attempt_count": 19,
        "run_count": 9,
        "total": 0.2854256
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 33.91999537453004,
      "contributing_entrants": null,
      "distinct_rated_opponents": 151,
      "draws": 114,
      "entry_count": 5,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:46Z",
      "losses": 110,
      "max_score": 60.49902848103273,
      "measured_at": null,
      "min_score": 5.6844327646508575,
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.3730012455485,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 29.284489531532348,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 218,
      "capped_draws": 30,
      "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": 0.09705768,
        "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": 28.986209582318256,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 159,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 183,
      "max_score": 45.067797325096485,
      "measured_at": null,
      "min_score": 13.449884255838182,
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.300908323919,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 28.03454044029496,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 486,
      "capped_draws": 45,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 46
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.02904086,
        "mean": 0.020196066154166664,
        "median": 0.0210709803,
        "min": 0.0085050301,
        "recorded_attempt_count": 46,
        "run_count": 21,
        "total": 0.426437947
      },
      "codegen_evaluated_cells": 21,
      "conditional_success_score": 30.44884977751772,
      "contributing_entrants": null,
      "distinct_rated_opponents": 243,
      "draws": 381,
      "entry_count": 30,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.047619047619047616,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:23Z",
      "losses": 317,
      "max_score": 39.642986122725766,
      "measured_at": null,
      "min_score": 25.616057609593227,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 6,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.84113861512,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 14,
      "repaired_rate": 0.6666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.992319252943247,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 374,
      "capped_draws": 18,
      "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": 0.08145696
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 30.97000026471277,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 116,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:41Z",
      "losses": 163,
      "max_score": 36.47987858051721,
      "measured_at": null,
      "min_score": 17.078759313374523,
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.9665230506514,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.98455429099188,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 252,
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0056201515,
        "mean": 0.0029446039375,
        "median": 0.001956843,
        "min": 0.001266762,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.029176983000000004
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 29.440367187054477,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 130,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:15:48Z",
      "losses": 209,
      "max_score": 51.81286686979948,
      "measured_at": null,
      "min_score": 17.993252641418948,
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.5204361339454,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.64757882677474,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5,
      "attempted_matches": 188,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.08193244999999999,
        "mean": 0.05495368125,
        "median": 0.056941025,
        "min": 0.02174195,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.43962945
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.017555673697316,
      "contributing_entrants": null,
      "distinct_rated_opponents": 94,
      "draws": 59,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:46:13Z",
      "losses": 179,
      "max_score": 41.14537153635741,
      "measured_at": null,
      "min_score": 19.747298274267855,
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.8647719765709,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.57894030213595,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6,
      "attempted_matches": 356,
      "capped_draws": 54,
      "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": 0.0149315,
        "mean": 0.00915140625,
        "median": 0.00943475,
        "min": 0.00402875,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.07321124999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.49097663317166,
      "contributing_entrants": null,
      "distinct_rated_opponents": 178,
      "draws": 92,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:40Z",
      "losses": 164,
      "max_score": 41.996828952531544,
      "measured_at": null,
      "min_score": 6.21180309294096,
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5685590383966,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.44444615449602,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 618,
      "capped_draws": 149,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 28.769437863151424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 309,
      "draws": 305,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 223,
      "max_score": 44.48159231995547,
      "measured_at": null,
      "min_score": 18.886821253244385,
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 618,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.2087654477366,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 25.58004949521818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 156,
      "capped_draws": 10,
      "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": 0.10247140625,
        "median": 0.113468875,
        "min": 0.061553,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.8197712500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.867639901120747,
      "contributing_entrants": null,
      "distinct_rated_opponents": 78,
      "draws": 49,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:50:59Z",
      "losses": 172,
      "max_score": 40.20162634486448,
      "measured_at": null,
      "min_score": 1.8004338185596558,
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.418672774443,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 24.77822512127107,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 167,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.0264053125,
        "median": 0.022682375,
        "min": 0.01946775,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.2112425
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.04212337597506,
      "contributing_entrants": null,
      "distinct_rated_opponents": 84,
      "draws": 106,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:34:29Z",
      "losses": 169,
      "max_score": 37.72719101235718,
      "measured_at": null,
      "min_score": 16.251044990851373,
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 167,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.942761941479,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 24.044225601614347,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 333,
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.039679950000000005,
        "mean": 0.029276065625,
        "median": 0.0306386,
        "min": 0.01864685,
        "recorded_attempt_count": 33,
        "run_count": 16,
        "total": 0.46841705000000006
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.44908019609191,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 294,
      "entry_count": 18,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:46:59Z",
      "losses": 193,
      "max_score": 32.441158944802936,
      "measured_at": null,
      "min_score": 24.546803091037,
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.4594864632938,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 23.771600760331932,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 490,
      "capped_draws": 73,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.17574199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.58929565473188,
      "contributing_entrants": null,
      "distinct_rated_opponents": 245,
      "draws": 204,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:56:04Z",
      "losses": 220,
      "max_score": 42.723936908981315,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 489,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.120605397401,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 23.58929565473188,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.341716425,
        "mean": 0.30867194062500003,
        "median": 0.31836633750000004,
        "min": 0.2745495,
        "recorded_attempt_count": 33,
        "run_count": 16,
        "total": 4.9387510500000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 62.82337105668461,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 106,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:19:08Z",
      "losses": 59,
      "max_score": 90.24764585966038,
      "measured_at": null,
      "min_score": 35.39909625370884,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 8,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.5,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.2287904366156,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 8,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 52.82794751572005,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 158,
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.055222,
        "mean": 0.046879,
        "median": 0.046959,
        "min": 0.039474,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.375032
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.58771087910249,
      "contributing_entrants": null,
      "distinct_rated_opponents": 79,
      "draws": 12,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "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
      },
      "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": "2026-07-27T15:55:08Z",
      "losses": 136,
      "max_score": 51.34913352806587,
      "measured_at": null,
      "min_score": 36.12527583054917,
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0725512767813,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.06171397988976,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16,
      "attempted_matches": 694,
      "capped_draws": 158,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 347,
      "draws": 259,
      "entry_count": 16,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 198,
      "max_score": 70.22812208032087,
      "measured_at": null,
      "min_score": 23.923663197046043,
      "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": "provisional",
      "rated_matches": 694,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.2152098230015,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 44.32614214103149,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 340,
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 138,
      "entry_count": 8,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:46:59Z",
      "losses": 100,
      "max_score": 55.113612498782416,
      "measured_at": null,
      "min_score": 25.620538806917818,
      "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": "provisional",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9656335191942,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.73044836931286,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 1188,
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 594,
      "draws": 342,
      "entry_count": 28,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:40Z",
      "losses": 435,
      "max_score": 54.02396836927419,
      "measured_at": null,
      "min_score": 26.01512692587781,
      "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": "provisional",
      "rated_matches": 1188,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8590454079178,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.05094350246561,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 411
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 342,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 102,
      "entry_count": 8,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:10Z",
      "losses": 132,
      "max_score": 56.36684029870736,
      "measured_at": null,
      "min_score": 22.30259680139711,
      "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": "provisional",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1314133867284,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.70475670619771,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 438,
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.2156775,
        "mean": 0.157461515625,
        "median": 0.15705206249999998,
        "min": 0.098579625,
        "recorded_attempt_count": 33,
        "run_count": 16,
        "total": 2.51938425
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 46.31080487287338,
      "contributing_entrants": null,
      "distinct_rated_opponents": 218,
      "draws": 181,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 139,
      "max_score": 69.71683172233598,
      "measured_at": null,
      "min_score": 26.222888398882304,
      "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": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.1656686637784,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.66403487978772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 298,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 149,
      "draws": 98,
      "entry_count": 7,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:51:15Z",
      "losses": 114,
      "max_score": 53.57169863410424,
      "measured_at": null,
      "min_score": 21.20665469801167,
      "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": "provisional",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.0615511034816,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.68218931552467,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 218,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.0371769625,
        "median": 0.029592175,
        "min": 0.02387735,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.2974157
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.07034239208697,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 94,
      "entry_count": 4,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:28Z",
      "losses": 66,
      "max_score": 54.04373188325387,
      "measured_at": null,
      "min_score": 32.28302107896658,
      "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": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.8607062781928,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.5359036907486,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 600,
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 300,
      "draws": 228,
      "entry_count": 14,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:17Z",
      "losses": 236,
      "max_score": 51.468109335875496,
      "measured_at": null,
      "min_score": 23.975023785065247,
      "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": "provisional",
      "rated_matches": 600,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3505140835375,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.19606995047676,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.213668025,
        "mean": 0.180929025625,
        "median": 0.1746528825,
        "min": 0.16318875,
        "recorded_attempt_count": 37,
        "run_count": 16,
        "total": 2.8948644100000003
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 44.11619405789825,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 73,
      "entry_count": 5,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T02:15:57Z",
      "losses": 80,
      "max_score": 56.06167167227131,
      "measured_at": null,
      "min_score": 21.717457965632377,
      "model_code_failure_rate": 0.6875,
      "model_code_failures": 11,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "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": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.5821063001963,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 32.984548508298495,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5,
      "attempted_matches": 210,
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 105,
      "draws": 141,
      "entry_count": 5,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:40:08Z",
      "losses": 44,
      "max_score": 51.785443642756896,
      "measured_at": null,
      "min_score": 21.77927935287923,
      "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": "provisional",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3539522692658,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.789261679901063,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 34,
        "run_count": 15,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 36.619351291593446,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 84,
      "entry_count": 7,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "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
      },
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T04:32:32Z",
      "losses": 130,
      "max_score": 42.88368038241504,
      "measured_at": null,
      "min_score": 30.355022200771856,
      "model_code_failure_rate": 0.5333333333333333,
      "model_code_failures": 8,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4666666666666667,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.4495589461794,
      "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.4666666666666667,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.266509720644656,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 284,
      "capped_draws": 59,
      "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": 0.0429946875,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.67062590477188,
      "contributing_entrants": null,
      "distinct_rated_opponents": 141,
      "draws": 64,
      "entry_count": 4,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 130,
      "max_score": 38.2909369413615,
      "measured_at": null,
      "min_score": 26.072194902063597,
      "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": 281,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.4837759080667,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.472612207417814,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 3,
      "wins": 87
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 218,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 58,
      "entry_count": 5,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:31Z",
      "losses": 111,
      "max_score": 41.40382647576317,
      "measured_at": null,
      "min_score": 0.0,
      "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": "provisional",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.9966234633323,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 23.538864797348666,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 344,
      "capped_draws": 116,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.02527583517874,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 116,
      "entry_count": 5,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:05Z",
      "losses": 164,
      "max_score": 27.522770043194065,
      "measured_at": null,
      "min_score": 26.527781627163417,
      "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": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.4107181713196,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 20.20610664115091,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 142,
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.33185775,
        "mean": 0.18266821875,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 1.7932034999999995
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.868711903025027,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 19,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:30:30Z",
      "losses": 195,
      "max_score": 28.913374800215543,
      "measured_at": null,
      "min_score": 15.499927748138225,
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.8775248484535,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 17.8557284981134,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:16Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1904.3194643073384,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:32Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1840.8511544908365,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 92.11822076992448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:45Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1823.1594383472432,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 89.30637072728769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:16Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.2827891456054,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 77.04163766987543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T10:47:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.2957199694602,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 75.64277085800467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:37Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.569380601013,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.6465473220185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:35Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.451007353691,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.96939634840618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.3589534729288,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.57544686267458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:25Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.4310233167598,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.72123593215844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T10:48:01Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.604801686931,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.15810496914253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 210,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 105,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.8861943996365,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.72208019034245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.74831355425182,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T11:21:33Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.9498843243437,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.24070868286577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 98,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 49,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.62225026505,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.73590439615545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.97783371817835,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:34Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.161593705389,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.35576459451039,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:15Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.5515776650714,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.04667059518091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.289805193975,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.48880272697796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.385247984007,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.78504534403884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:30Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.5380641852346,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.81280359013286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:26Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.388491274526,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.484582777796334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.5607673020877,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.188964919420734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.6415648788145,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.06172320072071,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:19Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.485564292801,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.99108950548842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:46Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.2591240187812,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.47714496936588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:21:38Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.6537688986575,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.905585560065134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 42,
      "draws": 69,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:41Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.9822709107812,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.62451221481294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.111817092302566,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 16,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:28:50Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.4332627403917,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.22022924708464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:15Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.1781720591457,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.98896235225361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.6962238815845,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.894074601780616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:45Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.0858652952545,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.36684029870736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 42,
      "draws": 67,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:14Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.8684946102,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.03078053724524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.111817092302566,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:03Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.340614191469,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.81582799890011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:18Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.6926849361364,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.57169863410424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 128,
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 64,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.68828391194,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.45198302770152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.13401041481541,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.3730974136329,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.16535532101704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:45:00Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.3715719552615,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.81286686979948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.6714120111717,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.4344292839315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:46Z",
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.38343795476,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.01923123018594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-26T01:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.954612695839,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.015291423254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:31:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.3692703367008,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.478057624072626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 60,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 30,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:16Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.586354924754,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.45152450798648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.534862397692415,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.0632638630816,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.37802087647134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.8435026888779,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:25:02Z",
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.8471484037084,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.06691150878728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-26T05:08:25Z",
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.8238828088404,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.02997089758741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.322471283357,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.80453019713377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 62,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:40Z",
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.1257108359016,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.79163908116498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 28,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:06Z",
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.425377493292,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.636647445449704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 68,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:55:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.216784303636,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.62917908688148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 220,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 110,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.600222806797,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.38658897369575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.375101550890244,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:33:29Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0945784086714,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.82185440133597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.71727501641449,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:35Z",
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.438796086254,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.374389594950806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T10:47:58Z",
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.114031725191,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.66102087130642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:46Z",
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.1795477973849,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.521519400812174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.928225102148446,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:05Z",
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.8070614799876,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.42169278538346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-26T04:33:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6576382024014,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.65575530999811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:33:08Z",
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.5618038162802,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.64312313421955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:45Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2237959132,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.5724430344671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:00:39Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9655056194315,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.52251713937394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.5771573742084,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.48159231995547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 45,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:25Z",
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.9593531656378,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.40416072069643,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 76,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.5007886172232,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.39699646208931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 184,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 92,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:40Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.8955897479009,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.215606466401034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.232085339282207,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:47:44Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.4008078994289,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.20979035442635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 194,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 97,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:52Z",
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.206308236593,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.96692548864581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.28106122889297,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:10Z",
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.7292262906526,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.909739239921585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T10:33:16Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3793905117934,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.996828952531544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0417343596705,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.78310808513646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 46,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.7618017769018,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.62441000493686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:15Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.9172858681118,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.327363323089216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.7562594006596,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 37,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:15Z",
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.7687348778354,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.27037605502182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.81642880532208,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:35Z",
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.0631482289907,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.23843353793476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 66,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 33,
      "draws": 67,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.8259144795377,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.09999373395438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.804469689928176,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:15Z",
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0064719759512,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.837923897204504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T04:31:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.3176275999922,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.001139620161496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:45Z",
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.0798296671542,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.007186117752184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 270,
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 135,
      "draws": 78,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.3174388329098,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.65857398163143,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.763148331401503,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 220,
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 110,
      "draws": 70,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:48Z",
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8409082389398,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.58749680418459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.356468484757592,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:06Z",
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.142971092423,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.8499002021569,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 3,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.3393264056997,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.427216277491794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:46Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.8200847740486,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.23244384036473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.40903824311957,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:34Z",
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.3232146087823,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.87536426896172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.6757984989108,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.44544070850067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.854093299657,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.474295630021714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:34Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.448577341908,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.896390308583022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.190176438217,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.28492958888438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:24Z",
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.9198897376532,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.44129093251917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:28:50Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.552660186412,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.32612813598716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:40Z",
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.5463193317332,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.522770043194065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.606750070474943,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:41Z",
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.444300552325,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.253758174484467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.163404047537,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.63272439732407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-07-27T11:47:56Z",
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.0645693107565,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.53737468779395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T08:33:33Z",
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.399703918666,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.974404110127313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.60640070509,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.776628277424983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:24Z",
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.1499854705874,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.77927935287923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-26T02:12:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.2264010041774,
      "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.778009667965605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.5005645283743,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.747298274267855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 228,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 114,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.340560614945,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.10293660731239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.96682519692495,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:50Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1778.6483184624055,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:56Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.1613209336665,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 90.09571894996164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:50Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.158468705878,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 78.54184751328685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:16Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.515391796302,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 73.19703425601392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 51,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:38Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.82345004235,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.61344185255442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:59Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1624.69812777023,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.452640140055266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.3314720438675,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.80363707825724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:54Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.2143177522778,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.273546807227696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.434703520284,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.201035877446856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:04Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.3008269640052,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.45287871885732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 82,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.4679193719608,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.82965387274463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.490506449776696,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:56Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.714251788026,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.00382249149155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 39,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T07:55:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1746719119114,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.748923171140326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 33,
      "draws": 79,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.1302271015347,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.890496423277526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.4017714074875,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:04Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4621431048597,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.18281284883366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 68,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T14:52:06Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.6155054033272,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.962548767694756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:15Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8766895584683,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.97531310705538,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:06Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.5716831996058,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.61416074557098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:01Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.383120170803,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.60246582139271,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 88,
      "draws": 168,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:05Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.668846160256,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.22481911643467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.00449926204939,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 119,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T14:52:08Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9605922249866,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.72052116086004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.501056091277,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.664876400707286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3686744490708,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.37203516308192,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:28Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.901542637513,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.28302107896658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.7746335763547,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.56362733585045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:05Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.1855742024472,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.406715690809293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 62,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.2182531123694,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.0661415287832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 120,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:13Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.279944881233,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.789942968134213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.189585591546,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.68951048376554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.0475371244402,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.6467494525862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.5622315860544,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.06424289135372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 116,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:13Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.5867943828466,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.985200935164713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 104,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:00Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.7128017422178,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.692155158998496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 164,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 82,
      "draws": 151,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:59Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6343566374824,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.662876822386636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.36169251502154,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1407076693067,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.486147225977007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4728086634052,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.40359272291873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3,
      "attempted_matches": 175,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 88,
      "draws": 146,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:58Z",
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 175,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.7873247436503,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.39591170776535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.200730137000697,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.9783044216706,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.188858982099404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:14Z",
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.3396386261843,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.041029137757743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "draws": 105,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:54Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.01344851071,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.93961926553232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.955126495349,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.936859423853782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 67,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:30Z",
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.5827653330884,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.89812236139288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:04Z",
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0802986534875,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.832423610551896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:18Z",
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.6106392697473,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.830010796441194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5798481424442,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.82265996372679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 60,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:34Z",
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5865175875335,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.71454218394329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 56,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T10:49:51Z",
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.3293696473902,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.65315269754207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 73,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-26T04:32:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.683594336881,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.548198358769575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.75968834662516,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 167,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 84,
      "draws": 153,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 167,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4503257520255,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.51048338744381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.91557794393657,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 234,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 117,
      "draws": 216,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:13Z",
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.9194358272002,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.45383607650836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.29857046522331,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-26T02:19:22Z",
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.219893880294,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.422755456149947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 123,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3566802074506,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.41673240515275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:36Z",
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.792058417232,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.19843674091044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.0639451591423,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.146372762679754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 79,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.3621960045764,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.97926320645363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:02Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9611713998297,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.705611244015376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:53Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.57787505147,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.542272343102017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.39456088374059,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:12Z",
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.784359152328,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.461582006857626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 60,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:28Z",
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.6963835500655,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.360571887099717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 53,
      "draws": 169,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:05Z",
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8761702774934,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.32744061084774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.39228737690977,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:42Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4827683360977,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.675502781911693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:52Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4547971192335,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.35973023478462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 62,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:23:51Z",
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.8989139702087,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.272777344588157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 76,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-26T01:22:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0646296592502,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.237099338958902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:06Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4715871938947,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.222888398882304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 44,
      "draws": 161,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:01Z",
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6601257834463,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.08750560023417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.11452287836695,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.175080615072,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.085553048269652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 112,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:13Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.9731336346329,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.07854941714752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.052677204897826,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-26T02:16:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3188858458,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.059066298254493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 57,
      "draws": 103,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.716589613089,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.01512692587781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T09:04:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.0637410889549,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.620538806917818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 37,
      "draws": 113,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:56Z",
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.9285932914202,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.35927855243578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.01309903675748,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T09:17:42Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.361568758212,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.189567064800336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 18,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5847832126149,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.85962983613944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 70,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.171016892196,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.975023785065247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:19Z",
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.374121179378,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.923663197046043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:39:38Z",
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5720084631907,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.668410863923103,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-25T18:00:56Z",
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.7957048023695,
      "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.06938008129636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-26T02:14:07Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.91270724254,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.858580155536725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3741079493293,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.69204681390362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4432660242555,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.61535944594515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 40,
      "draws": 113,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:23:51Z",
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.518205022639,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.54265599085522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.4839229723041,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 104,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.363891896275,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.27615981022488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 53.222204280998206,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 35,
      "draws": 139,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.797947792316,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.918128242024164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.35362439738494,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.958193352233,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.82093118555568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 53,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:01Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.505213110513,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.82577587485795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:07Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1819.3735501939025,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 99.01750849232472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:22Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.1898306547898,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 92.5436481576926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T08:03:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.207188118948,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.09760234044293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 34,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.3300278167235,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.45308478035796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.90444889821687,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:28Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.350902249458,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.14974362057465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:57Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.7951447614212,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.77578508926699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:22Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.5282621482136,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.66421699198599,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:15Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.9570166952826,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.26320303032371,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:55Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.920108094656,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.08227965708637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-26T04:32:18Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.3665103598798,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.09081208170358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.092140040724,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.1033903036507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.6158310169712,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.67575600395128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:59Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.5793891002238,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.01828026826074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:26Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.1619524841408,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.688836210667226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:17Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.3471653061004,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.468109335875496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:40Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.1875388618716,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.412762414887055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-26T04:27:36Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.381974984623,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.32372030022173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 160,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 80,
      "draws": 72,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.4968144156458,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.491486811514505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.73999395147524,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 156,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 78,
      "draws": 96,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.103686313155,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.38643236051798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.02849041872271,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 49,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.9087960092234,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.09192000149523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1810017274283,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.94286785536366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:36Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.648010167357,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.72936122718848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 51,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:31:38Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.547181905224,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.5426251223461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T10:18:25Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 39,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.6990353724188,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.27053092873559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.30694150420948,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 20,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.3650099625977,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.7391225197325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 53.834496495328466,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:20Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.356600835827,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.43891826866166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-26T02:12:12Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9062245881858,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.42582526757698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 136,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 68,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:52Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.2563755535427,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.22471380142931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.01758738954685,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T14:55:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.323955650604,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.38385520211626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:04Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.7556987902174,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.10653317662637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.8716525415657,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.62802340349199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.4987104220186,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.0058977081419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 61.71645590010924,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:17Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.572800589371,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.7143796127683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:52Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.4273983408475,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.29390245547429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-26T01:22:06Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.8495357628185,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.85985057751497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T09:13:01Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.9188274128549,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.723936908981315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2660520172667,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.495274622791904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T08:02:37Z",
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.3469365962942,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.329296821438945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 52.64737393979195,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 51,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:30Z",
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6623509478843,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.985067425141104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 124,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 62,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8677869593969,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.63731750642038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.435575077886185,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:18Z",
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.092226074721,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.56307486091444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.51728889973289,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:40Z",
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.357755308563,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.03053983455878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-26T03:31:46Z",
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.5254254199208,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.239662184794696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.63358145932378,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:40Z",
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0826808498505,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.20162634486448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 54.36252243246881,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:03:28Z",
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0062111246496,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.192204570731214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:47Z",
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.8977257302613,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.82116655919238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 55.70579806569183,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:02Z",
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 21,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.6707577765233,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.7702372055603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 59.5501790889026,
      "unilateral_faults": 1,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 18,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.5326664526883,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.2217430159087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 180,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 90,
      "draws": 66,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:13Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.958429102522,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.82859840268824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.65033652638543,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T10:18:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0530820785134,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.82631568621353,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:56Z",
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.7826005116174,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.6391638686108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:59Z",
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.2674122393996,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.461208791388664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T14:53:14Z",
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.0101184596929,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.16178607693494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.381307433771,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.64090722117748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 92,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 46,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.018589518323,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.38298276714462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.13137666820794,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.3679574628934,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.706944523905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:11Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.666473249807,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.4921765950404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.304426701457977,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 21,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2165792620408,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.8662064154452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.38915666892314,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:41Z",
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6445964503675,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.485660760472555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 28,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.1372881816976,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.34188785207999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 48,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:15Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.3051991222185,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.39410414668713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:00Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.1096514863327,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.38334591324993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.8441074111074,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.68336617958372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 54.80243805853167,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T09:28:28Z",
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.3860603587646,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.050446121101896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.099303746516,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.63120574976151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.825348329168,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.14898379651178,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:31:27Z",
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.179191434123,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.055991271142776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:51Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.0705798788915,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.48358424139654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:07Z",
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2608906471414,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.440225048579062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.38271273642583,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 39,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.9156680808603,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.684453538846107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.295968555715895,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:21Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.207385463267,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.61584059577335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:49Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1821.3947826255776,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:00Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.9563654007216,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 73.33281812779559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-26T05:17:50Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.9321943610776,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.37465172530936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.789369331552,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.43667406598968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:35:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.2220685254226,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.3067010884318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:56Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.4078028250656,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.43603009561291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:17Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.2329284352627,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.169539127004974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:17Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.1896956500836,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.655504012060575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T10:30:15Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.4093381266223,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.412604814752626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 54,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:35Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.2912045583273,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.01330799880638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.70344991379835,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.1716734247516,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.15488856869603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 178,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 89,
      "draws": 119,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.5090589843633,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.31882962012266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.863176880820333,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 47,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:46Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.0760172985165,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.17117874326892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.49878111612754,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:09Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.1890238694712,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.84036755746706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8145480172825,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.34401724523379,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:29:48Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.9773873174586,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.2849917916824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:25Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8170890563797,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.13791710250739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:55Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.367240999507,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.06024334765576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 71,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:06Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.0291620852558,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.465613636603344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T08:31:20Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.025896067843,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.78259187031759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 14,
      "draws": 16,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:39Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.8999918600214,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.70878194898091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.09766908852594,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T14:55:10Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.129620533277,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.60853817575416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:59Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.558199870668,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.42523001417078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.95048007367414,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:46Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.736546987583,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.29062220793382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T10:43:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.8853854171534,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.08519776719661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:01Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0229127508078,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.977121778303186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 37,
      "draws": 75,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.109269958217,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.848221051862794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.76160072203399,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.5933624248837,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.697311929291594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:13Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.8215591763649,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.630719839920246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 208,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 104,
      "draws": 152,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:13Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.1670799235726,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.01628425017713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.30650400938057,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:43Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.700299003465,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.564843479998515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:38Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7518112619032,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.47987858051721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.4916414654292,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.004894996193826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:52:49Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.1061108254105,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.99123440741221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9868494776583,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.78712902503984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 158,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 79,
      "draws": 112,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:32Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.409438596447,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.711020849728605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.83117993386317,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 55,
      "draws": 90,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:56Z",
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.4317047269096,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.188797475282726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.137368732378228,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T10:43:48Z",
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.518146546648,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.29690331835047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 102,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:28Z",
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.0281178076189,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.290379711385775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.27287274483318,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:08Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.0471982021531,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.22189995892514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 129,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 87,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:22Z",
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.6071390852817,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.207432320938985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:21Z",
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.460996966201,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.11255787082396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:28Z",
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.4002724512168,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.96421938799026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 92,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:40Z",
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.696435624508,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.74918488008487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:40Z",
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2296172501635,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.4691324962955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9339395098796,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.30566532198333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9190911735002,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.302708753199845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:30Z",
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.512832959456,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.49114002888361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 52.673834544262974,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.2693853856194,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.263089858934286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 39,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:33Z",
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.9701197438192,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.22275482443267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 190,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 95,
      "draws": 139,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8175269280712,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.17685443336674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.77768935251636,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:06Z",
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4876650964738,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.11930845299747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 82,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4789629339475,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.86936940191663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.03477987847802,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 56,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:23Z",
      "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": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5058004589516,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.642255258124266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.4284617057842,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.510166457816872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:49Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.3598482849127,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.921753926830576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:23Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.5119436507632,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.856816919223707,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 90,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0544037106083,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.50702629256417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 82,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.7594087580565,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.443391993025433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.08718040460786,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.243599728563,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.880664924292944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T08:27:58Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9783565501152,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.86715418711666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 57.22830710326107,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 66,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.404391708064,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.815219490526346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.453330167729,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.732078673060073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:01Z",
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9817668716055,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.16636028907312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:31Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9614593543852,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.129670210091273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:55Z",
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.450385706255,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.996130934586745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 17,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:38Z",
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.8102858634056,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.274656356852365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:06Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2980270082412,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.837372334700223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.62023516889464,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T10:10:02Z",
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.8799045162689,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.82583876113024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:04Z",
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.4129665430028,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.735143570454905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.9056700157024,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 88,
      "draws": 149,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:53Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.8644480597122,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.36600328835098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.53736994289201,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:49:59Z",
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9356837685343,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.3472600456232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:12Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.048658197518,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.292620478258247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 57.22830710326107,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:21Z",
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.8766306909731,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.590043215791468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 52.673834544262974,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.351636088787,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.30965713552444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.027768011903404,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 90,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9312245396438,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.264406825032907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 53.555037320705495,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 38,
      "draws": 78,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.51206013175,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.225821636295716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.75459128937461,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 45,
      "draws": 136,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:23Z",
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.5819924358773,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.616057609593227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.16991582857914,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-26T02:19:07Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.5657189380322,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.068514273806112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 17,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-26T22:08:31Z",
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.143974925331,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.956096391857447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.4221707921552,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.588513823342623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-26T04:32:32Z",
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9467799653128,
      "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.44151957954682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 46,
      "draws": 125,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:31Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.091767956876,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.60066630811733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.45913581389002,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T10:34:01Z",
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.214332474687,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.27152769675579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 39,
      "draws": 108,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:27Z",
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.3641057916232,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.82665639057853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.908551952141345,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 28,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T04:07:10Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5662249585166,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.58250517714516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-26T03:03:30Z",
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.206661663024,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.49239768223592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.39318729849085,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 16,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:57Z",
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6129486635432,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.637247385879313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.76941398892446,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T00:21:27Z",
      "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": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5853927038256,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 17.993252641418948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.027768011903404,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 12,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.6541457347726,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 11.042241208882738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 56.25,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1933.7094741760584,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 96.57379066170128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.678809124274,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 92.3708669015868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:29Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1859.1162007965604,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 86.37300771504712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:30Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1822.9563803754577,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 83.82486081338791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:49Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1823.6955807261916,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 83.50388880910803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:46Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.8199679947602,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.55197914748385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-26T05:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1807.478590078014,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.52103910064591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:20Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1760.1833865422625,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.6585459712308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1752.4021108928348,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.1510189524612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:26Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.892992498132,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.56906281561947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:44Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.169873719953,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 70.6997686167247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.60765757439077,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:13Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.336443752434,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.855634801012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.361567975806963,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:46Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.4542713590818,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.11245564094769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:48Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.6315145680098,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.43323967778432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:36Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.6046296590218,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.925284579574985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.928056527532547,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.9193174279271,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.024239354593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 137,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:49Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 137,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.7103540889234,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.786700401424746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.22717850480214,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:26Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.385772117564,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.86232872007845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:33Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.9630027424323,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.44226639021666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:35Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.5434120737496,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.42732881438667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:15Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.708544050022,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.863348614056285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.472525230101,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.77411458095119,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:38:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.596774461676,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.00415603353663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T10:36:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4768033532573,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.04373188325387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:00Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.3013243910782,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.89561753299053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:46Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.696901925296,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.736898671389504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:00Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.9046996706184,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.39903902878851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.8549313784958,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.92663955035931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:14Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.229860059093,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.829711260628585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.946042395649414,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.6378956784858,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.35911215449047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:28Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8298949184382,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.31323520003257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:17Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.729583417106,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.946312445904134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:21Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.8716690403694,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.2770740935357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.0151173817317,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.53327801033048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.0274446215944,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.38845226238323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.2272824362703,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.261687320285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:15Z",
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.701516438078,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.983757275316115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.0252991014984,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.41155335314362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.5904299300091,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.31725364553898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:42Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.9858286719375,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.94334155048709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:33Z",
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.9682819146449,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.87639190655733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.46393572312315,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 210,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 105,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.623822330184,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.517867682604326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.625289791427727,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:48Z",
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.9007927839396,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.456236804374136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.6286930837043,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.414031779727786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T08:40:46Z",
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.4398301501867,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.887127379709426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 46.62023516889464,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 97,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 97,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.7035184605436,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.80140024106329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.11849350131416,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:38Z",
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.312238039986,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.42219609913933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:12Z",
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.29536649102,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.232953795131394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.699748644724702,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:33Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.600072103669,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.921853226556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.6303220574653,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:09Z",
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9038956193683,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.11609569421241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.39456088374059,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 82,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9017846994225,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.76625876366004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.140758159376915,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:08Z",
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.1170634631212,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.73585500348754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:52Z",
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.032997627639,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.730006809943795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T10:25:28Z",
      "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": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.8580015094933,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.09912275717949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:14Z",
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.516113452013,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.97799867637564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T15:07:01Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.8308552065046,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.99990230008747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:13Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.412712328678,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.43956011342773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 66.24964258315117,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:19Z",
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0856341696644,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.14537153635741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.70587299553475,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.8515472914996,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.575444671868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:08Z",
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.2102640235487,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.46122645082023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:47Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.4451277035855,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.279547984289245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-26T04:30:24Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.5662528868663,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.968487196864096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 192,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 96,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.9972224389992,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.8544724665147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-07-27T10:17:43Z",
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.8208589793223,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.642986122725766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.974394715408586,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.0802873129855,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.3681250027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.6221436835365,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.39386082118144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.361567975806963,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.928615167466,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.2909369413615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 254,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 127,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:17Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.5578285667934,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.084940854795306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.59154576158009,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.1478710815124,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.08421464409825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:59Z",
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.5767315502376,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.35580390238191,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 71,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8705390548175,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.15666178716489,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.179828253878972,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 172,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8007026347743,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.65467092606256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.721842944692018,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T15:00:38Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.093697253425,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.28769585919104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:50Z",
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.6250464267923,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.28745751743145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 69.22474682633933,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.244405392198,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.48079904046824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.501367016649,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.69618438144857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:00Z",
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8102664408416,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.13361761793311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.3905933062547,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.3847722466155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T08:38:42Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.96843152589,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.2543519338834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.3047231017686,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.441158944802936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.253662717865495,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.2963219883493,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.957262612735185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:23Z",
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.323659481682,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.68905148984333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.3104206683065,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.02260862106261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.6669903963675,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.947553431989036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 202,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 101,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:14Z",
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.7739734730787,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.101312271875415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.913911453098134,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.5945266252224,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.9170413033881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.7941697138317,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.12678637185235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:34Z",
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.074507007328,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.32514751690616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.288827977848925,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-26T02:19:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.8823575046931,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.62168789866385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:12Z",
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.63995352344,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.39821775319491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 210,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 105,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.07449543575,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.279090243345703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.74831355425182,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:33Z",
      "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": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.8709361070892,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.85378503399073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.099984749541,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.22225700698019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:45Z",
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.022394286137,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.18853644184757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.6134001853593,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.379233976999053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:30Z",
      "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": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.784860201679,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.284916786321386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:34Z",
      "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": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.0234481385794,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 16.251044990851373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.39456088374059,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:58Z",
      "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": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.3323160300529,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 14.65937731419278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:47Z",
      "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": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.799664295561,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 13.449884255838182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1106.586721726533,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.322614521401,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 91.83061764137966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:08Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.502473660851,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 90.24764585966038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:35Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1779.224826819665,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 89.6862854041758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:36Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.1459218022244,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 89.13691320039523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 18,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:44Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1768.0118763760397,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 86.61766309589059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.2297854950075,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 83.55834325082338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:44Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1718.0303169897015,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 82.20988966457762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:35Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.5493909205152,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.12004893199418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 66,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.2585711313377,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 79.84257508312278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:32Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.484096247477,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 79.72428872775545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:17Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.7457177478934,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 78.42707203303546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:51Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1683.650875040015,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 77.20302117516688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:21Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.089981134785,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.4748305783871,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:02Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.6556396548986,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.15659509023824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:32Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1674.832336171311,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.1429991599217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:45:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1676.3558507059174,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.11062624621614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.6232412385289,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 73.07850759598226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:51Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.2207187307338,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 71.69384651100232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.165952256158,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 71.14412736694287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 43,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.527767943735,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 70.22812208032087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.9657064331486,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.79293959997881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:08Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.082997776762,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.153570024744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 34,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.524073532141,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.20962819187783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.07920226560997,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.2514891902983,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.09932142027597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 43,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T16:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.421943677852,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.27022799576758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.01679293279406,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.8608666300522,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.24239570415726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.6186674821492,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.09200456336322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.9904173149405,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.786908880400794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:36Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.0930229588678,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.424425877527234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.828244408040035,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.710166277599,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.50686447534633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.95999312316211,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.571475807063,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.49902848103273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 188,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 94,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.6253544498152,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.00481551608911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.9490803264906,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T10:41:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.7099847887985,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.51052506806163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.4551680393024,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.57756631923615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:15Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7759859246476,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.498007875599185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.531656885091,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.3837110637506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.5732183679058,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.32634647961873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 69,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:16Z",
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.2640974459423,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.081285429963856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.315587721029885,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-26T01:20:52Z",
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.3338889332665,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.06167167227131,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:03Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0458901456975,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.76800622889098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 260,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 130,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:16Z",
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.740122695648,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.56433079370909,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26167841562456,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:41Z",
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.7733406383302,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.83012501610077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-26T04:34:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.088754825532,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.39524382491415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:39Z",
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.184208348665,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.62283719668116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:38Z",
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.7647648288262,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.406674111573565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:56Z",
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.0097462451129,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.54958566492595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:18Z",
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.0471700351973,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.53892965023924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:36Z",
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.5581163462753,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.43282213007789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T10:46:50Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.4965294796054,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.41858338546655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:33Z",
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.76159895558,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.785443642756896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-26T03:28:35Z",
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.2599469181591,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.68826178338193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 38,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.5653877312857,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.643221073026574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 51.74125868734754,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.208213223521,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.22582047612717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.406710872713,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.8631353550523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 46,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.829079283679,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.6663365380428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.67271236609984,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0980280128524,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.2174811242672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.8121397572054,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.03659155745648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 182,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:32Z",
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.631257835851,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.35863966481747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.127117585218937,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.7533405191086,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.279690469131054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.542154271933,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.151391350129174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 35,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:14Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.8609860751917,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.237594115915286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.817992173360395,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 168,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 84,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.883227109784,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.40962689886413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:21Z",
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3056015259317,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.684186833033415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.4552403692137,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.10102860564115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-07-27T11:59:44Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.6038581939165,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.45601398414009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8254161871469,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.40382647576317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T10:39:35Z",
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.707189128953,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.03021293974064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:16Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.5160558304942,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.88114678411723,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.6574813704308,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.796634638618634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.487204134739892,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:02Z",
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.6659693492472,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.43999875124963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:13Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.4926583834322,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.244509748458896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.462269258808135,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:42Z",
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.6201022386813,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.16937604000977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:58Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.0385830541572,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.17202473580983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:08Z",
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.013744309396,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.35881917136978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.4473281980904,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.31788335875319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:48Z",
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.7430753287372,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.249112314196054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:30Z",
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.884883080069,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.60391173446151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:07Z",
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.343401868112,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.35319203148646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:44Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.5529020758545,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.33434993833325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-07-26T02:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.0664771587387,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.84809500658452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:16Z",
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.2096633702972,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.66934396725515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:41Z",
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.5858526769046,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.63163240739917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:36Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.579754559503,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.49761345604342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:43Z",
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.2957907129323,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.401527305050784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:01Z",
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.9567117344586,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.703202638038128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T16:01:47Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.8150715027673,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.547572564793132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:37Z",
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.265412750451,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.979620323137993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 35,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:32Z",
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.51918938241,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.791817765880385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 37.948705117938445,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "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": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.5600157396711,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.620679713560136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.355683254666296,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.3542233252822,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.469471573505537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.3201234614855,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.43111022257915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:39Z",
      "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": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.3506475607678,
      "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.355022200771856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-26T02:14:14Z",
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.1063201840943,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.523236321771144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T10:45:10Z",
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.670844139026,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.913374800215543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-07-27T10:45:13Z",
      "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": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.332669440063,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.544824407056502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 43,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.2973248119208,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.104126773830203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.76180671258,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.335737306568312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.9692131063861,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1243.4193512828674,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.886821253244385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1174.1929957595082,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 9.219198794244829,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-26T05:16:44Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1910.1513048995253,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 98.99816924724276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.7924577346591,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 91.89097628140996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.285337815342,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 90.82151908302892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:02Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.87837198572,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 88.02796582947613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.2492100095503,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.99600365638999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:25Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.0788730945349,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 78.56920080122724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1730.0831070176853,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.23053193535173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.50491251305893,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.961634672591,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 75.98738578456185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:48Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.24753254842,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.0322843616957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:20Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.1651313142668,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.71683172233598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:13:39Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.4015620035889,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.09254323204925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:24Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.249574240341,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.54305795364324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.7266168626888,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.28650528900698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 206,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.0601903035,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.10151548866789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.603769221136574,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:00Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.6855421123205,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.08919562986975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 76
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-26T05:17:45Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.62727187213,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.72298874215366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.007726186437235,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:48Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.802982390646,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.58294385391025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:00Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6157786139568,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.912194201697034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:20Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.8782657464328,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.93013963759991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.730475331812,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.90248060999168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T08:36:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.041766542292,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.284218510036965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.0640499121846,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.066265662847066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.749923309519133,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:24Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.40868111242,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.39391405879897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:53Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.641725509094,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.13352254421294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.027897449992,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.90860829604776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.8243127331189,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.83351636895526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.007726186437235,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:47Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.3056410970028,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.63055697544416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.090637048514616,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:52Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.4603703334396,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.31929094075836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.334374414189384,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:45Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.8705167678413,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.29494455453205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T10:15:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.920523238979,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.25034027872709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:45Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.2842653226814,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.41621180403329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.69173419161021,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.584014782258,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.327402124523715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:22Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.596224581565,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.113612498782416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:55Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.1316071761985,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.36584442360475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 50
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 70,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:40Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.4031788330378,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.02396836927419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.68118764215533,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:26Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5834431296869,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.462360625353874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 70,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.293623643294,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.42069139868415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 31.933316946790622,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:14Z",
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.78268960349,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.355787870899725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.928225102148446,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:46Z",
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.179287904116,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.14134044954261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:22Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.8649438145444,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.53268699210788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.815994700812965,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:20Z",
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.9260778582047,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.93322035186378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.267903630526114,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.630215711361,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.05114074851961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:10Z",
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.3262272831655,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.944407671620375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:10:13Z",
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7496459810498,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.45212194783904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:05Z",
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9594139977837,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.34867560826997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.3871953975538,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.86100001987165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:14Z",
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.8456094590335,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.82415975623741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 195,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 195,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.7194140114843,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.586159297967185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.932937500005405,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:45Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.0077416215331,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.68324115546186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:17Z",
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.4607367338915,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.067797325096485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.9315472806888,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:31Z",
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.8556102937082,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.9018165077582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.82405236779077,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.320314512178,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.8546337721922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:08Z",
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.2974094270803,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.66391737325167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.6059977114926,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.20700574081687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.016004726288628,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:19Z",
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.253043117009,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.995121216025154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.39318729849085,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:43Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.628492568711,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.2871495944819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:24Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.9750388104458,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.899176885906776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-26T01:23:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.9282613982691,
      "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.88368038241504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.3127110418286,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.96115933902756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:03Z",
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.8552075834623,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.89162392193896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9620516903908,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.87578726019612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.979783736733566,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:23Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.3423615846004,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.873011049349245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T08:07:41Z",
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.2959606735676,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.35812772742118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.462269258808135,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T10:17:46Z",
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.3195981523795,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.03137150213544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.9315472806888,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:17Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.5096246302887,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.53812602283009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2235891986847,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.50337610769172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 48.73444152250164,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:13Z",
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8610596627066,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.3880018617899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:53Z",
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.0948620707277,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.72719101235718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:10Z",
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3527923761658,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.622454286388646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.3656681646023,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.12643857527608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 216,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.985570579499,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.07982876915568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.814596123589618,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6260556799098,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.12527583054917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:20Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.2743046740543,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.55977304408127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:58Z",
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.2392931700497,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.91319206814089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.5863858748698,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.620804135772225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.570138866854082,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.3110822405563,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.10621141460972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.74936409813348,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:23Z",
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4098434956095,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.55029327378088,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 64.59124787447364,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-26T02:15:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.587035593027,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.59598125820875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.7423245669345,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.35976589284266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:13Z",
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.3333503741408,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.908555878820593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:48Z",
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.7298482608094,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.031275607799287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:48Z",
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.4160981986215,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.66929794584434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:52Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.71662390316,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.094119565026094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:10:12Z",
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.8159516092887,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.816413152201964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:14Z",
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0992001492057,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.49197066564704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:05Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.1995227607265,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.527781627163417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.689982844879,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.82251025654144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 233,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-07-27T11:38:30Z",
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.782192176075,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.682571481279417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.353618598248712,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 192,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 94,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.983665204464,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.486420364689437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.282056102542683,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T10:36:04Z",
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.8016849909914,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.20665469801167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.571115310678,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 17.769416290858764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.801044736378422,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.5505253206957,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 17.078759313374523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:55Z",
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.4479943480187,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 15.499927748138225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.8599986467784,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 13.7890857228278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:13Z",
      "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": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.0530232290791,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 6.21180309294096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.348522168338,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 5.6844327646508575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:40Z",
      "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": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1134.1894705301404,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:56Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1912.1873848057296,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 192,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 96,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:21Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1819.9291865090927,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 85.57962471129208,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.532640791940832,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:18Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.30238195533,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 74.41108271929163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:50Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.7828651797977,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.280987550827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 40,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:03Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.3794583194792,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.13253570322934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.15312037953302,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:02Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.1796710479507,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.76630327200057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:50Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.1260261745642,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.02884715553996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 57,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.9837411017909,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.66486562803726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.178218158143345,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:46Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1689.6876237550243,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.475663086016624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:28Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1669.5691004601476,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.23123191335946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T15:19:58Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.365116897373,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.99415499988833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.4486548697253,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.15070675443215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:24Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.5524233506335,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.934388839397826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.3208067268397,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.84580662581403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 40,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:03Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.277878301726,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.712424267511985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 50.2932617637271,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:56Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.734946206889,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.34913352806587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-26T05:11:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.9619175578798,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.27239116238635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:29Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.8431949043122,
      "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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.853328871691126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:10Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.5237946011143,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.85247714738262,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.27072293001,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.70296063793118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:43Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.9180516740412,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.483919215225825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3,
      "attempted_matches": 216,
      "capped_draws": 107,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 108,
      "draws": 107,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.60438067143,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.36624656479914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.80281801640143,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:33Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.5977769607723,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.00561736197007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.288827977848925,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 70,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.5485274057612,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.79474327591976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.68118764215533,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T09:17:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.706490224709,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.47739221194158,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:16Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.6287669745502,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.55996968426065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 190,
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 95,
      "draws": 93,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.115041857068,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.10145974217034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.6518151147346,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:29Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.549910317883,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.44282331296946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 98,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 49,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.500717693615,
      "reasoning_level": "Extended thinking (legacy shared budget)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_exact",
          "request_mode": "effort",
          "requested_effort": "legacy_shared_thinking_budget",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Extended thinking (legacy shared budget)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "legacy_shared_thinking_budget",
        "reasoning_bucket_label": "Extended thinking (legacy shared budget)",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "legacy_shared_thinking_budget"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.915510291216975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.895858543560735,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.7738994568635,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.39909625370884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T10:37:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.409453460546,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.69828421039091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:27Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.812720862631,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.63468032269175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.036461425079892,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 292,
      "capped_draws": 184,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 146,
      "draws": 184,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:09Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.3505911967395,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.476964983236684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.393742914134872,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.6642579295235,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.45351907819096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 198,
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 99,
      "draws": 88,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.680872206851,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.224440808203862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.42733990918024,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T09:14:03Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.521515251263,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.356162068590265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 44,
      "draws": 81,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:31Z",
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7862356855082,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.20997390701733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.006220619850886,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T10:03:23Z",
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.8759114421637,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.996350093562853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1357275132184,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.95785357363107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 66,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:44Z",
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.1375092603982,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.75956752250197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:40Z",
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.0417625819548,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.47922458032685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:20Z",
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3879047496516,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.475476864323102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T10:35:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.9222743715295,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.41687597028761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:46Z",
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.5903871925957,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.006597636421393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T10:42:50Z",
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.1797497732612,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.903404995054014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.4863124214994,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.305825631962907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:34Z",
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.9523521591466,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.090589774286613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 62,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.6514940291925,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.74641003392749,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 115,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 70,
      "draws": 115,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:11Z",
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8942718475291,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.69893190865684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.68118764215533,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 55,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.099914328351,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.543654388822937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3787650864267,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.40244569391851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:26Z",
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.883097011328,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.30638809711645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T14:50:07Z",
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9671606777888,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.049679476012503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.873384161387,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.035172472656587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:26Z",
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.6488483482228,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.919709973327855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:47Z",
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.5140773232674,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.83423634499792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:47Z",
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.791824430241,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.754628515692527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5298755363042,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.69416926616589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 188,
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 94,
      "draws": 112,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4570082099108,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.657621512898544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.04868740318581,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 53,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.1437448693234,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.58497915083693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:07Z",
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.793708185056,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.439052410696952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:10Z",
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9480224880604,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.15877822959248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:30Z",
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.104133950512,
      "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": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.12237999875593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 72,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:44Z",
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.9991933165616,
      "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.087039515938308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 53,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:59Z",
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.5092940470956,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.072194902063597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 46,
      "draws": 83,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:07Z",
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.2618465194205,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.99208014269019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:34Z",
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.727549023724,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.811146558890066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.1969593602666,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.746626341753977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3,
      "attempted_matches": 214,
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 148,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.161544741987,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.69338379391731,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.220668586617483,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:10Z",
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.8659054082534,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.548654376833127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:50Z",
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3808697764316,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.48617559035576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 39,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:08Z",
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4563174105635,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "highest",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.403373868757644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 208,
      "capped_draws": 160,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 104,
      "draws": 160,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:30Z",
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.5055080741283,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.35335800760461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.898126228636851,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:37Z",
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.324273248414,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.340296080038364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:14Z",
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.7695118803483,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.19884765587022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.564493870363,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.09160686347721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 115,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "draws": 115,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:06Z",
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.3637798159552,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.05809791299054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.606750070474943,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:39Z",
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.5283788982229,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.85647924437633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:00Z",
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.7730988237663,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.57930679395035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.48716501561997,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 109,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:44Z",
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0502690810122,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.546803091037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 39.34626684974488,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "draws": 113,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:12Z",
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9833201414342,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.225753638009312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.606750070474943,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 69,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.7246740268902,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.13090597526191,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:08Z",
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.5832665791972,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.01162765730244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T14:49:23Z",
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.1465689714887,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.944071579260378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 119,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:07Z",
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.85097822939,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.58388507203711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.377800258513927,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 44,
      "draws": 103,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:59Z",
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.93041194247,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.515456529989933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.11029391633042,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:01Z",
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.0774072462827,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.30259680139711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 33,
      "draws": 66,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:44Z",
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5413044631157,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.15179482155793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 45.56239790693811,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 71,
      "draws": 93,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.5687072472667,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.04868244275925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.179828253878972,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-26T02:14:59Z",
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.7532402504671,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.717457965632377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:45Z",
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.4353933526995,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "minimal",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.513590194658597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 103,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 103,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:01Z",
      "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": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.9721409206004,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "none",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.416862714154615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:31Z",
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.4738925482284,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "medium",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.44814764085012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:47Z",
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.1341743107275,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.585628377608835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.288827977848925,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:21Z",
      "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": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.907367827263,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.57553453515884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.816045493821,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.13272808568275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 67.16844047215152,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:21Z",
      "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": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.1765488406536,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "high",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.014153696699164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:25Z",
      "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": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.9378527645924,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 15.99986870925893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:59Z",
      "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": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.3511651122055,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "enabled",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 1.8004338185596558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 49.76941398892446,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 40,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 40,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 48
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 8,
        "max": 2.09943,
        "mean": 0.703821875,
        "median": 0.48028875,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 48
        },
        "run_count": 48,
        "token_priced_attempt_count": 48,
        "total": 33.78345000000001
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 40,
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 40,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:29Z",
      "losses": null,
      "max_score": 99.01750849232472,
      "measured_at": null,
      "min_score": 43.13791710250739,
      "model_code_failure_rate": 0.16666666666666666,
      "model_code_failures": 8,
      "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": 1703.221690780623,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 67.55600869152525,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 1.078263125,
        "median": 0.5065824999999999,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 28
        },
        "run_count": 24,
        "token_priced_attempt_count": 28,
        "total": 25.878314999999997
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 24,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:13Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 25.189567064800336,
      "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": 1609.1992785224372,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 57.785527760572016,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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-2026-07-25": 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,
      "entry_count": 24,
      "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
      },
      "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": "2026-07-27T15:58:56Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 15.99986870925893,
      "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": 1584.3508842894803,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.038461538461538464,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 56.29728534700427,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 59,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 59,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 104
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.1445437333333333,
        "mean": 0.08597182777777779,
        "median": 0.08538879999999999,
        "min": 0.041110400000000005,
        "recorded_attempt_count": 104,
        "run_count": 64,
        "total": 5.5669699999999995
      },
      "codegen_evaluated_cells": 64,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 91,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 27,
      "first_pass_rate": 0.421875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 16,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:13Z",
      "losses": null,
      "max_score": 85.57962471129208,
      "measured_at": null,
      "min_score": 20.684453538846107,
      "model_code_failure_rate": 0.078125,
      "model_code_failures": 5,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.0844714429193,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 32,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 52.125341188188095,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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-2026-07-25": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 26.566350000000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 22,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:56Z",
      "losses": null,
      "max_score": 88.02796582947613,
      "measured_at": null,
      "min_score": 27.049679476012503,
      "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": 1577.477813295176,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 51.70012612911366,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 0.203055,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 10.45624
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 22,
      "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
      },
      "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": "2026-07-27T16:02:24Z",
      "losses": null,
      "max_score": 77.20302117516688,
      "measured_at": null,
      "min_score": 26.35973023478462,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.8509344298914,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.65832605641348,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 49,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 97
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.9392418,
        "mean": 0.3752466458333333,
        "median": 0.32150055,
        "min": 0.0587988,
        "recorded_attempt_count": 97,
        "run_count": 55,
        "total": 22.9788486
      },
      "codegen_evaluated_cells": 55,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 88,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.2909090909090909,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:01:47Z",
      "losses": null,
      "max_score": 68.20962819187783,
      "measured_at": null,
      "min_score": 21.27615981022488,
      "model_code_failure_rate": 0.10909090909090909,
      "model_code_failures": 6,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.3187904251258,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 33,
      "repaired_rate": 0.6,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.62028157243777,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 12.13752,
        "mean": 2.8005991666666663,
        "median": 0.158095,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 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,
      "entry_count": 24,
      "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
      },
      "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": "2026-07-27T16:02:13Z",
      "losses": null,
      "max_score": 72.0322843616957,
      "measured_at": null,
      "min_score": 27.543654388822937,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.346708797123,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.28,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.583546974620106,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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-2026-07-25": 28
        },
        "run_count": 26,
        "token_priced_attempt_count": 28,
        "total": 29.297331000000007
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 24,
      "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
      },
      "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": "2026-07-27T15:57:30Z",
      "losses": null,
      "max_score": 76.4748305783871,
      "measured_at": null,
      "min_score": 0.0,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.7671770348747,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.07692307692307693,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.3080362215951,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 59,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 59,
        "cell_count": 23,
        "cost_basis_counts": {
          "local_standard_estimate": 70
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.5164726249999998,
        "mean": 0.3999331141304348,
        "median": 0.2331955,
        "min": 0.01259225,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 70
        },
        "run_count": 60,
        "token_priced_attempt_count": 70,
        "total": 18.42633
      },
      "codegen_evaluated_cells": 60,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 59,
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 51,
      "first_pass_rate": 0.85,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": null,
      "max_score": 66.08919562986975,
      "measured_at": null,
      "min_score": 21.486420364689437,
      "model_code_failure_rate": 0.016666666666666666,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.9917265167776,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 8,
      "repaired_rate": 0.13333333333333333,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 39.98893967882885,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 47,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 47,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 89
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.04815395,
        "mean": 0.025957827083333333,
        "median": 0.02516155,
        "min": 0.00845595,
        "recorded_attempt_count": 89,
        "run_count": 48,
        "total": 1.2459757000000002
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 46,
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.20833333333333337,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:23:13Z",
      "losses": null,
      "max_score": 65.72298874215366,
      "measured_at": null,
      "min_score": 14.65937731419278,
      "model_code_failure_rate": 0.020833333333333332,
      "model_code_failures": 1,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.1264393173703,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 37,
      "repaired_rate": 0.7708333333333334,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.09699938126408,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 65,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 65,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 130
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 16,
        "max": 0.38568888333333334,
        "mean": 0.10861519774305556,
        "median": 0.025206018750000003,
        "min": 0.0058062875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 130
        },
        "run_count": 81,
        "token_priced_attempt_count": 130,
        "total": 6.1442372999999995
      },
      "codegen_evaluated_cells": 81,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 65,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 33,
      "first_pass_rate": 0.4074074074074074,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 9,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": null,
      "max_score": 55.56433079370909,
      "measured_at": null,
      "min_score": 19.10293660731239,
      "model_code_failure_rate": 0.19753086419753085,
      "model_code_failures": 16,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3116299208316,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 32,
      "repaired_rate": 0.3950617283950617,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.492095492125856,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 47
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.01660212,
        "mean": 0.004222185916666667,
        "median": 0.0025298300000000003,
        "min": 0.00045831,
        "recorded_attempt_count": 47,
        "run_count": 24,
        "total": 0.101332462
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-01",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:23Z",
      "losses": null,
      "max_score": 61.50686447534633,
      "measured_at": null,
      "min_score": 11.042241208882738,
      "model_code_failure_rate": 0.16666666666666666,
      "model_code_failures": 4,
      "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": 1463.2486372874646,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 14,
      "repaired_rate": 0.5833333333333334,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.292055103935187,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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-2026-07-25": 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,
      "entry_count": 15,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:59Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 50.169539127004974,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 73.4445721362937,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 24
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.29615479166666664,
        "median": 0.1968175,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 16,
          "boardgame-list-prices-2026-07-25": 8
        },
        "run_count": 24,
        "token_priced_attempt_count": 24,
        "total": 7.107714999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:41Z",
      "losses": null,
      "max_score": 59.15070675443215,
      "measured_at": null,
      "min_score": 35.18281284883366,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 47.14570999192436,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 40,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 82
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.341716425,
        "mean": 0.17334414687500002,
        "median": 0.166217925,
        "min": 0.029012250000000003,
        "recorded_attempt_count": 82,
        "run_count": 48,
        "total": 8.320519050000001
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 40,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-07"
      ],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": null,
      "max_score": 90.24764585966038,
      "measured_at": null,
      "min_score": 22.04868244275925,
      "model_code_failure_rate": 0.16666666666666666,
      "model_code_failures": 8,
      "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": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.386714110605,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 24,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.94208557765952,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6921525,
        "mean": 0.41891503125,
        "median": 0.4031475,
        "min": 0.254883,
        "recorded_attempt_count": 37,
        "run_count": 16,
        "total": 6.702640499999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 20,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": null,
      "max_score": 89.30637072728769,
      "measured_at": null,
      "min_score": 18.014153696699164,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 14,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.441856340894674,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 0.121855,
        "mean": 0.05695140625,
        "median": 0.036751875,
        "min": 0.015285,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.9112225
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 21,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:01:47Z",
      "losses": null,
      "max_score": 80.99600365638999,
      "measured_at": null,
      "min_score": 29.188858982099404,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.51804778866547,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 16,
        "cost_basis_counts": {
          "local_standard_estimate": 19
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.454645,
        "mean": 0.22978835937499997,
        "median": 0.1997375,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 19
        },
        "run_count": 16,
        "token_priced_attempt_count": 19,
        "total": 3.67661375
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 23,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": null,
      "max_score": 62.786908880400794,
      "measured_at": null,
      "min_score": 24.57930679395035,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.90777511519566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 16,
        "cost_basis_counts": {
          "local_list_price_estimate": 19
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.4567,
        "mean": 0.2220434166666667,
        "median": 0.183367,
        "min": 0.05673,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-25": 17
        },
        "run_count": 18,
        "token_priced_attempt_count": 19,
        "total": 4.168735999999999
      },
      "codegen_evaluated_cells": 18,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 18,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:21Z",
      "losses": null,
      "max_score": 59.06172320072071,
      "measured_at": null,
      "min_score": 25.620538806917818,
      "model_code_failure_rate": 0.05555555555555555,
      "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": 1498.6482907847264,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.05555555555555555,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.78161722772243,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 18,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 29
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 6,
        "max": 0.136952,
        "mean": 0.056666249999999994,
        "median": 0.050531999999999994,
        "min": 0.03731,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 24,
        "token_priced_attempt_count": 29,
        "total": 1.35999
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 26,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5833333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "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": "2026-07-27T15:54:23Z",
      "losses": null,
      "max_score": 86.61766309589059,
      "measured_at": null,
      "min_score": 18.13272808568275,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 6,
      "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": 1524.3452446978067,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.225829250873645,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 57
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.25293804044999996,
        "mean": 0.19953128278324997,
        "median": 0.20662718916666667,
        "min": 0.13279406625,
        "recorded_attempt_count": 57,
        "run_count": 27,
        "total": 5.24138213703
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 63,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.037037037037037035,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:37:08Z",
      "losses": null,
      "max_score": 70.22812208032087,
      "measured_at": null,
      "min_score": 23.923663197046043,
      "model_code_failure_rate": 0.2962962962962963,
      "model_code_failures": 8,
      "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": 1510.4790823777164,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 18,
      "repaired_rate": 0.6666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.83054720506445,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 0.7872815620000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 13,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:21Z",
      "losses": null,
      "max_score": 76.6585459712308,
      "measured_at": null,
      "min_score": 20.61584059577335,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 8,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.70309058567017,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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,
      "entry_count": 17,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": null,
      "max_score": 67.54305795364324,
      "measured_at": null,
      "min_score": 25.340296080038364,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 8,
      "repaired_rate": 0.5333333333333333,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.17723329403148,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 45
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.00596013,
        "mean": 0.0023166812500000004,
        "median": 0.00193686,
        "min": 0.00093502,
        "recorded_attempt_count": 45,
        "run_count": 28,
        "total": 0.06608082
      },
      "codegen_evaluated_cells": 28,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 23,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.4642857142857143,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:51:17Z",
      "losses": null,
      "max_score": 58.47714496936588,
      "measured_at": null,
      "min_score": 23.58388507203711,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 10,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.91561209107624,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 8,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:10Z",
      "losses": null,
      "max_score": 56.36684029870736,
      "measured_at": null,
      "min_score": 22.30259680139711,
      "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": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.70475670619771,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 0.4852846
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": null,
      "max_score": 53.736898671389504,
      "measured_at": null,
      "min_score": 26.15877822959248,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 36.88241645259816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 57
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.04649778,
        "mean": 0.024494787749999997,
        "median": 0.022485588,
        "min": 0.004429524000000001,
        "recorded_attempt_count": 57,
        "run_count": 32,
        "total": 0.7838332080000001
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 26,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:13Z",
      "losses": null,
      "max_score": 52.54958566492595,
      "measured_at": null,
      "min_score": 19.49239768223592,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 6,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 18,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 36.30835591436927,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 1.2830031540000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:21Z",
      "losses": null,
      "max_score": 48.456236804374136,
      "measured_at": null,
      "min_score": 23.668410863923103,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.680425213671555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 32,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 81
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 13,
        "max": 0.02904086,
        "mean": 0.01148428059375,
        "median": 0.006669530066666667,
        "min": 0.00169122,
        "recorded_attempt_count": 81,
        "run_count": 45,
        "total": 0.4929778278
      },
      "codegen_evaluated_cells": 45,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 52,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.28888888888888886,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:23Z",
      "losses": null,
      "max_score": 51.785443642756896,
      "measured_at": null,
      "min_score": 21.77927935287923,
      "model_code_failure_rate": 0.28888888888888886,
      "model_code_failures": 13,
      "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": 1451.179015192513,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 19,
      "repaired_rate": 0.4222222222222222,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.709260009850475,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 28,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 102
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 20,
        "max": 0.213668025,
        "mean": 0.08694262229166666,
        "median": 0.059337825,
        "min": 0.012912625,
        "recorded_attempt_count": 102,
        "run_count": 48,
        "total": 4.17324587
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 28,
      "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": 0.14583333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:31:04Z",
      "losses": null,
      "max_score": 56.06167167227131,
      "measured_at": null,
      "min_score": 21.717457965632377,
      "model_code_failure_rate": 0.4166666666666667,
      "model_code_failures": 20,
      "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": 1460.921488718306,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 21,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.634319078319784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 0.7875583199999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 20,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:38Z",
      "losses": null,
      "max_score": 53.01828026826074,
      "measured_at": null,
      "min_score": 13.449884255838182,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 9,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.344667990638854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "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": 0.5164659200000001
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 18,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:41Z",
      "losses": null,
      "max_score": 59.51052506806163,
      "measured_at": null,
      "min_score": 17.078759313374523,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.4117647058823529,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.22196163051123,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 30,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 60
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.015971877,
        "mean": 0.006007524767083333,
        "median": 0.0031725295999999997,
        "min": 0.001825724,
        "recorded_attempt_count": 60,
        "run_count": 39,
        "total": 0.19590749698
      },
      "codegen_evaluated_cells": 39,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 44,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.4871794871794872,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": null,
      "max_score": 51.468109335875496,
      "measured_at": null,
      "min_score": 23.975023785065247,
      "model_code_failure_rate": 0.2307692307692308,
      "model_code_failures": 9,
      "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": 1428.1085324995604,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 11,
      "repaired_rate": 0.28205128205128205,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.11867834257186,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 55
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.08193244999999999,
        "mean": 0.03901218041666666,
        "median": 0.03030545,
        "min": 0.00984735,
        "recorded_attempt_count": 55,
        "run_count": 24,
        "total": 0.93629233
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 21,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.041666666666666664,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:43Z",
      "losses": null,
      "max_score": 54.04373188325387,
      "measured_at": null,
      "min_score": 19.57553453515884,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 8,
      "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": 1438.1999560190477,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 15,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 32.47819970422248,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0056201515,
        "mean": 0.00210600034375,
        "median": 0.0014932259999999998,
        "min": 0.00090937,
        "recorded_attempt_count": 24,
        "run_count": 17,
        "total": 0.039316157
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 20,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:55:05Z",
      "losses": null,
      "max_score": 72.6465473220185,
      "measured_at": null,
      "min_score": 17.993252641418948,
      "model_code_failure_rate": 0.2352941176470588,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.2352941176470588,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 32.01014225656428,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 14,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0092087,
        "mean": 0.004466478571428571,
        "median": 0.0042425399999999995,
        "min": 0.00144036,
        "recorded_attempt_count": 23,
        "run_count": 14,
        "total": 0.06253070000000001
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:42Z",
      "losses": null,
      "max_score": 44.39699646208931,
      "measured_at": null,
      "min_score": 22.18853644184757,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.288086375992073,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 12,
        "max": 0.2156775,
        "mean": 0.12996646093750003,
        "median": 0.12798825,
        "min": 0.061553,
        "recorded_attempt_count": 50,
        "run_count": 24,
        "total": 3.3391555
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 17,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": null,
      "max_score": 69.71683172233598,
      "measured_at": null,
      "min_score": 1.8004338185596558,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.2211300005294,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0445032,
        "mean": 0.030658954687500004,
        "median": 0.0312573,
        "min": 0.01864685,
        "recorded_attempt_count": 52,
        "run_count": 25,
        "total": 0.75384265
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 30,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.08,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:36Z",
      "losses": null,
      "max_score": 60.49902848103273,
      "measured_at": null,
      "min_score": 5.6844327646508575,
      "model_code_failure_rate": 0.44,
      "model_code_failures": 11,
      "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": 1463.6267091764323,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.48,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 29.579426535796316,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 63
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 14,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 63,
        "run_count": 31,
        "total": 0.0
      },
      "codegen_evaluated_cells": 31,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 17,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.1935483870967742,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": null,
      "max_score": 44.48159231995547,
      "measured_at": null,
      "min_score": 18.886821253244385,
      "model_code_failure_rate": 0.4516129032258064,
      "model_code_failures": 14,
      "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_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": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 11,
      "repaired_rate": 0.3548387096774194,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.92327960793142,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 13,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 44,
        "run_count": 24,
        "total": 0.0
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 17,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:12Z",
      "losses": null,
      "max_score": 43.2871495944819,
      "measured_at": null,
      "min_score": 19.585628377608835,
      "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_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": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333337,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 25.20969046694418,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0422995,
        "mean": 0.017778359375,
        "median": 0.017199625,
        "min": 0.00402875,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.28445375000000006
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 21,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:40Z",
      "losses": null,
      "max_score": 41.996828952531544,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.3125,
      "model_code_failures": 5,
      "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": 1311.7617461310865,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 9,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 25.00917885115301,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 27
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.33185775,
        "mean": 0.112831453125,
        "median": 0.0747585,
        "min": 0.0223935,
        "recorded_attempt_count": 27,
        "run_count": 17,
        "total": 2.137161
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.2352941176470588,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": null,
      "max_score": 38.2909369413615,
      "measured_at": null,
      "min_score": 15.499927748138225,
      "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.2352941176470588,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 22.66417035276561,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 732,
      "capped_draws": 7,
      "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": 0.4461796875,
        "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": 72.42802335561073,
      "contributing_entrants": null,
      "distinct_rated_opponents": 366,
      "draws": 103,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:50Z",
      "losses": 181,
      "max_score": 92.5436481576926,
      "measured_at": null,
      "min_score": 43.13791710250739,
      "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": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.6100169154984,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 70.0500817123776,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 448
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 396,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0372
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 65.57074160938022,
      "contributing_entrants": null,
      "distinct_rated_opponents": 198,
      "draws": 62,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:59Z",
      "losses": 108,
      "max_score": 75.98738578456185,
      "measured_at": null,
      "min_score": 50.169539127004974,
      "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": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.01775040059,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 63.41793679949243,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": 1528,
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12366493333333332,
        "mean": 0.09185773333333332,
        "median": 0.09170913333333332,
        "min": 0.04980146666666666,
        "recorded_attempt_count": 39,
        "run_count": 24,
        "total": 2.2045855999999997
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 61.02342972194618,
      "contributing_entrants": null,
      "distinct_rated_opponents": 763,
      "draws": 354,
      "entry_count": 23,
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.4166666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "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": "2026-07-27T16:02:13Z",
      "losses": 419,
      "max_score": 85.57962471129208,
      "measured_at": null,
      "min_score": 38.01628425017713,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.9583333333333334,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1528,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.304606454339,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": 13,
      "repaired_rate": 0.5416666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 60.377588250409744,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 755
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 452,
      "capped_draws": 7,
      "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": 0.366615,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 4.11992
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 59.534531948954026,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 103,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:58:56Z",
      "losses": 126,
      "max_score": 76.15659509023824,
      "measured_at": null,
      "min_score": 34.29690331835047,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.2424875928227,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 57.80705078732788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8,
      "attempted_matches": 460,
      "capped_draws": 57,
      "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": 52.23257256057504,
      "contributing_entrants": null,
      "distinct_rated_opponents": 229,
      "draws": 163,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 112,
      "max_score": 89.30637072728769,
      "measured_at": null,
      "min_score": 20.44814764085012,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 458,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.8911595246293,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 52.23257256057504,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1047,
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "max": 0.25698975,
        "mean": 0.172479834375,
        "median": 0.166217925,
        "min": 0.10864875,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 2.75967735
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 49.33456114316592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 523,
      "draws": 389,
      "entry_count": 16,
      "failed_game_aliases": [],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 268,
      "max_score": 79.84257508312278,
      "measured_at": null,
      "min_score": 22.04868244275925,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1046,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.7511937613583,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 49.33456114316592,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 389
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 484,
      "capped_draws": 49,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.989149999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.48149951346338,
      "contributing_entrants": null,
      "distinct_rated_opponents": 242,
      "draws": 181,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:20Z",
      "losses": 131,
      "max_score": 91.83061764137966,
      "measured_at": null,
      "min_score": 25.189567064800336,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0495869021083,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 48.48149951346338,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 454,
      "capped_draws": 65,
      "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": 0.442856875,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.542855
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.09744784101551,
      "contributing_entrants": null,
      "distinct_rated_opponents": 227,
      "draws": 153,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:56Z",
      "losses": 144,
      "max_score": 65.58294385391025,
      "measured_at": null,
      "min_score": 27.3472600456232,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.8784219094462,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 48.09744784101551,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 462,
      "capped_draws": 72,
      "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": 0.046574,
        "mean": 0.036155625,
        "median": 0.035338,
        "min": 0.025803,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 0.315048
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 48.32188705528165,
      "contributing_entrants": null,
      "distinct_rated_opponents": 231,
      "draws": 206,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T16:02:31Z",
      "losses": 127,
      "max_score": 65.24239570415726,
      "measured_at": null,
      "min_score": 30.356162068590265,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.046193867148,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.919757117419735,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 430,
      "capped_draws": 63,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.26724769418371,
      "contributing_entrants": null,
      "distinct_rated_opponents": 215,
      "draws": 166,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 121,
      "max_score": 77.20302117516688,
      "measured_at": null,
      "min_score": 26.35973023478462,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 430,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.898443627913,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.26724769418371,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 444,
      "capped_draws": 53,
      "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": 0.158095,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.33952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.35164383250624,
      "contributing_entrants": null,
      "distinct_rated_opponents": 221,
      "draws": 189,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T16:02:13Z",
      "losses": 121,
      "max_score": 52.41858338546655,
      "measured_at": null,
      "min_score": 30.06424289135372,
      "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": 444,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9457841650956,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.35164383250624,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 508,
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.3926418,
        "mean": 0.31750829999999997,
        "median": 0.32150055,
        "min": 0.2298153,
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 5.0801327999999994
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.64692033959544,
      "contributing_entrants": null,
      "distinct_rated_opponents": 254,
      "draws": 360,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-05"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.0625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:57Z",
      "losses": 204,
      "max_score": 68.20962819187783,
      "measured_at": null,
      "min_score": 21.27615981022488,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.9375,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 508,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.6308672353125,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 14,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.96434936980171,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 412,
      "capped_draws": 67,
      "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": 0.21477375,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.07706583204088,
      "contributing_entrants": null,
      "distinct_rated_opponents": 206,
      "draws": 143,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 136,
      "max_score": 57.29494455453205,
      "measured_at": null,
      "min_score": 26.83423634499792,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.1400277773191,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.66276865859234,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 366,
      "capped_draws": 45,
      "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": 0.03731,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.151619765977394,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 99,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:52:44Z",
      "losses": 132,
      "max_score": 57.32634647961873,
      "measured_at": null,
      "min_score": 27.82583876113024,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.6255950166408,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.087711891446865,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 222,
      "capped_draws": 27,
      "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": 0.121855,
        "mean": 0.09110296875,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.7288237500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.85260378513726,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 162,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:57Z",
      "losses": 137,
      "max_score": 67.28650528900698,
      "measured_at": null,
      "min_score": 29.188858982099404,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.5186198209324,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.47850789231176,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 168,
      "capped_draws": 27,
      "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": 0.0276132876,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.10999191243746,
      "contributing_entrants": null,
      "distinct_rated_opponents": 84,
      "draws": 86,
      "entry_count": 11,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:26:15Z",
      "losses": 156,
      "max_score": 61.78504534403884,
      "measured_at": null,
      "min_score": 25.340296080038364,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.9489718796042,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.11836794956651,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": 1351,
      "capped_draws": 173,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 26
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.29749325,
        "mean": 0.24155631250000004,
        "median": 0.24021375,
        "min": 0.17873725,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 5.7973514999999995
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 39.72454249564468,
      "contributing_entrants": null,
      "distinct_rated_opponents": 676,
      "draws": 496,
      "entry_count": 23,
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 22,
      "first_pass_rate": 0.9166666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 448,
      "max_score": 48.22471380142931,
      "measured_at": null,
      "min_score": 26.657621512898544,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 0.9583333333333334,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1351,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8797990384317,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 39.304117798140794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 407
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 426,
      "capped_draws": 53,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.624428
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.86834859384712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 213,
      "draws": 144,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:40Z",
      "losses": 134,
      "max_score": 50.22582047612717,
      "measured_at": null,
      "min_score": 27.035172472656587,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 426,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.663964902354,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.55939935050291,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 224,
      "capped_draws": 32,
      "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": 0.43500895999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.327281492102216,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 146,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:30Z",
      "losses": 122,
      "max_score": 59.51052506806163,
      "measured_at": null,
      "min_score": 26.919709973327855,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.2485760943189,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.45936897003059,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.04649778,
        "mean": 0.039593841,
        "median": 0.039509778,
        "min": 0.030762138,
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 0.633501456
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 39.88431631802561,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 126,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:11:55Z",
      "losses": 198,
      "max_score": 51.27239116238635,
      "measured_at": null,
      "min_score": 19.49239768223592,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.0975137826113,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.1165385675198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 252,
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.4852846
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.88241645259816,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 183,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:24Z",
      "losses": 168,
      "max_score": 53.736898671389504,
      "measured_at": null,
      "min_score": 26.15877822959248,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.093283579921,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 36.88241645259816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 184,
      "capped_draws": 2,
      "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": 1.2830031540000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.34111208929003,
      "contributing_entrants": null,
      "distinct_rated_opponents": 92,
      "draws": 97,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:21Z",
      "losses": 140,
      "max_score": 48.456236804374136,
      "measured_at": null,
      "min_score": 23.668410863923103,
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.2527923894484,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.680425213671555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 960,
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "max": 0.03261155,
        "mean": 0.02559155625,
        "median": 0.02516155,
        "min": 0.017927,
        "recorded_attempt_count": 32,
        "run_count": 16,
        "total": 0.4094649
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.76846744526695,
      "contributing_entrants": null,
      "distinct_rated_opponents": 478,
      "draws": 350,
      "entry_count": 15,
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.0625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:05Z",
      "losses": 341,
      "max_score": 49.5426251223461,
      "measured_at": null,
      "min_score": 17.769416290858764,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.0673219253688,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": 15,
      "repaired_rate": 0.9375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.76846744526695,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 263
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 716,
      "capped_draws": 35,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.07934969,
        "mean": 0.053583788125,
        "median": 0.0553142075,
        "min": 0.02549349,
        "recorded_attempt_count": 37,
        "run_count": 16,
        "total": 0.8573406100000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.83992960363705,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 188,
      "entry_count": 11,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-06",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:14Z",
      "losses": 291,
      "max_score": 53.355787870899725,
      "measured_at": null,
      "min_score": 30.50702629256417,
      "model_code_failure_rate": 0.3125,
      "model_code_failures": 5,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.6875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 716,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.688276622674,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": 11,
      "repaired_rate": 0.6875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.54570838202333,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 380,
      "capped_draws": 67,
      "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": 0.001130258,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.01972526
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.40505179177216,
      "contributing_entrants": null,
      "distinct_rated_opponents": 190,
      "draws": 180,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:23Z",
      "losses": 116,
      "max_score": 39.3681250027,
      "measured_at": null,
      "min_score": 29.486147225977007,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.5856012817162,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 32.308304150876324,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 1508,
      "capped_draws": 148,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 49
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 7,
        "max": 0.036200562500000005,
        "mean": 0.024352715625,
        "median": 0.025206018750000003,
        "min": 0.016582062499999998,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 49
        },
        "run_count": 32,
        "token_priced_attempt_count": 49,
        "total": 0.7792869
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 33.85869493427405,
      "contributing_entrants": null,
      "distinct_rated_opponents": 755,
      "draws": 415,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.40625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:57Z",
      "losses": 675,
      "max_score": 55.56433079370909,
      "measured_at": null,
      "min_score": 19.10293660731239,
      "model_code_failure_rate": 0.21875,
      "model_code_failures": 7,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.78125,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1508,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.445144486349,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 12,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.832278224424897,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 418
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 132,
      "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": 36.401921714481134,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 47,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:51:07Z",
      "losses": 110,
      "max_score": 43.730006809943795,
      "measured_at": null,
      "min_score": 29.16636028907312,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.1635317602309,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.64935029638511,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 22
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.00596013,
        "mean": 0.0023956312500000004,
        "median": 0.00186283,
        "min": 0.00105702,
        "recorded_attempt_count": 22,
        "run_count": 14,
        "total": 0.03542156
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 33.56861302601268,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 223,
      "entry_count": 11,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T04:30:24Z",
      "losses": 140,
      "max_score": 40.239662184794696,
      "measured_at": null,
      "min_score": 26.087039515938308,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.0114607809107,
      "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"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.604546286081508,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 180,
      "capped_draws": 25,
      "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": 32.46627609691285,
      "contributing_entrants": null,
      "distinct_rated_opponents": 90,
      "draws": 112,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:12Z",
      "losses": 144,
      "max_score": 43.2871495944819,
      "measured_at": null,
      "min_score": 19.585628377608835,
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.3850372603245,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.213274292737445,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 302,
      "capped_draws": 56,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0445032,
        "mean": 0.03204184375,
        "median": 0.0312573,
        "min": 0.0200767,
        "recorded_attempt_count": 19,
        "run_count": 9,
        "total": 0.2854256
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 33.91999537453004,
      "contributing_entrants": null,
      "distinct_rated_opponents": 151,
      "draws": 114,
      "entry_count": 5,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:46Z",
      "losses": 110,
      "max_score": 60.49902848103273,
      "measured_at": null,
      "min_score": 5.6844327646508575,
      "model_code_failure_rate": 0.4444444444444444,
      "model_code_failures": 4,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5555555555555556,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.3730012455485,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 29.284489531532348,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 218,
      "capped_draws": 30,
      "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": 0.09705768,
        "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": 28.986209582318256,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 159,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 183,
      "max_score": 45.067797325096485,
      "measured_at": null,
      "min_score": 13.449884255838182,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.300908323919,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 28.03454044029496,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 486,
      "capped_draws": 45,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 46
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.02904086,
        "mean": 0.020196066154166664,
        "median": 0.0210709803,
        "min": 0.0085050301,
        "recorded_attempt_count": 46,
        "run_count": 21,
        "total": 0.426437947
      },
      "codegen_evaluated_cells": 21,
      "conditional_success_score": 30.44884977751772,
      "contributing_entrants": null,
      "distinct_rated_opponents": 243,
      "draws": 381,
      "entry_count": 30,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.047619047619047616,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:23Z",
      "losses": 317,
      "max_score": 39.642986122725766,
      "measured_at": null,
      "min_score": 25.616057609593227,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 6,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.84113861512,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 14,
      "repaired_rate": 0.6666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.992319252943247,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 356,
      "capped_draws": 54,
      "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": 0.0149315,
        "mean": 0.00915140625,
        "median": 0.00943475,
        "min": 0.00402875,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.07321124999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.49097663317166,
      "contributing_entrants": null,
      "distinct_rated_opponents": 178,
      "draws": 92,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:40Z",
      "losses": 164,
      "max_score": 41.996828952531544,
      "measured_at": null,
      "min_score": 6.21180309294096,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5685590383966,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.44444615449602,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 156,
      "capped_draws": 10,
      "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": 0.10247140625,
        "median": 0.113468875,
        "min": 0.061553,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.8197712500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.867639901120747,
      "contributing_entrants": null,
      "distinct_rated_opponents": 78,
      "draws": 49,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:50:59Z",
      "losses": 172,
      "max_score": 40.20162634486448,
      "measured_at": null,
      "min_score": 1.8004338185596558,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.418672774443,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 24.77822512127107,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 694,
      "capped_draws": 158,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 347,
      "draws": 259,
      "entry_count": 16,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 198,
      "max_score": 70.22812208032087,
      "measured_at": null,
      "min_score": 23.923663197046043,
      "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": "provisional",
      "rated_matches": 694,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.2152098230015,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 44.32614214103149,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 218,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.0371769625,
        "median": 0.029592175,
        "min": 0.02387735,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.2974157
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.07034239208697,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 94,
      "entry_count": 4,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:28Z",
      "losses": 66,
      "max_score": 54.04373188325387,
      "measured_at": null,
      "min_score": 32.28302107896658,
      "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": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.8607062781928,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.5359036907486,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 600,
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 300,
      "draws": 228,
      "entry_count": 14,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:17Z",
      "losses": 236,
      "max_score": 51.468109335875496,
      "measured_at": null,
      "min_score": 23.975023785065247,
      "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": "provisional",
      "rated_matches": 600,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3505140835375,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.19606995047676,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 34,
        "run_count": 15,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 36.619351291593446,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 84,
      "entry_count": 7,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "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
      },
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T04:32:32Z",
      "losses": 130,
      "max_score": 42.88368038241504,
      "measured_at": null,
      "min_score": 30.355022200771856,
      "model_code_failure_rate": 0.5333333333333333,
      "model_code_failures": 8,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4666666666666667,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.4495589461794,
      "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": 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"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.4666666666666667,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.266509720644656,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:45Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1823.1594383472432,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 89.30637072728769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:35Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.451007353691,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.96939634840618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:25Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.4310233167598,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.72123593215844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 210,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 105,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.8861943996365,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.72208019034245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.74831355425182,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T11:21:33Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.9498843243437,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.24070868286577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:15Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.5515776650714,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.04667059518091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.385247984007,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.78504534403884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.5607673020877,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.188964919420734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:19Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.485564292801,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.99108950548842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:21:38Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.6537688986575,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.905585560065134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.6714120111717,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.4344292839315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:46Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.38343795476,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.01923123018594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-26T01:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.954612695839,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.015291423254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:31:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.3692703367008,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.478057624072626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.812854461075986,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 60,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 30,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:16Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.586354924754,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.45152450798648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 41.534862397692415,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.0632638630816,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.37802087647134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.8435026888779,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.322471283357,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.80453019713377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:33:29Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0945784086714,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.82185440133597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 41.71727501641449,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:05Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.8070614799876,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.42169278538346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:33:08Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.5618038162802,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.64312313421955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 45,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:25Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.9593531656378,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.40416072069643,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 194,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 97,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:52Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.206308236593,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.96692548864581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.28106122889297,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T10:33:16Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3793905117934,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.996828952531544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0417343596705,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.78310808513646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 46,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.7618017769018,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.62441000493686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 37,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:15Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.7687348778354,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.27037605502182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.81642880532208,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.3393264056997,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.427216277491794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:46Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.8200847740486,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.23244384036473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.40903824311957,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.6757984989108,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.44544070850067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.854093299657,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.474295630021714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:24Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.9198897376532,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.44129093251917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:41Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.444300552325,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.253758174484467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-26T02:12:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.2264010041774,
      "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.778009667965605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 228,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 114,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-07-27T11:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.340560614945,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.10293660731239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.96682519692495,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 51,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:38Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.82345004235,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.61344185255442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:59Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1624.69812777023,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.452640140055266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.434703520284,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.201035877446856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 82,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.4679193719608,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.82965387274463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.490506449776696,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:56Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.714251788026,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.00382249149155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.501056091277,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.664876400707286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:28Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.901542637513,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.28302107896658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 120,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:13Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.279944881233,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.789942968134213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.189585591546,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.68951048376554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.0475371244402,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.6467494525862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.5622315860544,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.06424289135372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 164,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 82,
      "draws": 151,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:59Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6343566374824,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.662876822386636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.36169251502154,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1407076693067,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.486147225977007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.9783044216706,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.188858982099404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 67,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:30Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.5827653330884,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.89812236139288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.80145244019624,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:18Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.6106392697473,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.830010796441194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 167,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 84,
      "draws": 153,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 167,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4503257520255,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.51048338744381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.91557794393657,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-26T02:19:22Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.219893880294,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.422755456149947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 123,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3566802074506,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.41673240515275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:36Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.792058417232,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.19843674091044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 79,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.3621960045764,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.97926320645363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:12Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.784359152328,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.461582006857626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:52Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4547971192335,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.35973023478462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 88,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 44,
      "draws": 161,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:01Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6601257834463,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.08750560023417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 47.11452287836695,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T09:17:42Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.361568758212,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.189567064800336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 70,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.171016892196,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.975023785065247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:19Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.374121179378,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.923663197046043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:39:38Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5720084631907,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.668410863923103,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-25T18:00:56Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.7957048023695,
      "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.06938008129636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4432660242555,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.61535944594515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 104,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.363891896275,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.27615981022488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 53.222204280998206,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:22Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.1898306547898,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 92.5436481576926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:57Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.7951447614212,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.77578508926699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:22Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.5282621482136,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.66421699198599,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:15Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.9570166952826,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.26320303032371,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.966995223862348,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:17Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.3471653061004,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.468109335875496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 46.05265101338746,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 160,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 80,
      "draws": 72,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.4968144156458,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.491486811514505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.73999395147524,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 51,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:31:38Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.547181905224,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.5426251223461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 20,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.3650099625977,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.7391225197325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 53.834496495328466,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 136,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 68,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:52Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.2563755535427,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.22471380142931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.01758738954685,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.8716525415657,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.62802340349199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:52Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.4273983408475,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.29390245547429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-26T01:22:06Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.8495357628185,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.85985057751497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:40Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.357755308563,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.03053983455878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 46.05265101338746,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-26T03:31:46Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.5254254199208,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.239662184794696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.63358145932378,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:40Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0826808498505,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.20162634486448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 54.36252243246881,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:03:28Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0062111246496,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.192204570731214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:47Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.8977257302613,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.82116655919238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 55.70579806569183,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:56Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.7826005116174,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.6391638686108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:41Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6445964503675,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.485660760472555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 28,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.1372881816976,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.34188785207999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.8441074111074,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.68336617958372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 54.80243805853167,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T09:28:28Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.3860603587646,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.050446121101896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.825348329168,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.14898379651178,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:17Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.2329284352627,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.169539127004974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.1716734247516,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.15488856869603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 178,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 89,
      "draws": 119,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.5090589843633,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.31882962012266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.863176880820333,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:09Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.1890238694712,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.84036755746706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8145480172825,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.34401724523379,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:25Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8170890563797,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.13791710250739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.966995223862348,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T08:31:20Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.025896067843,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.78259187031759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T10:43:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.8853854171534,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.08519776719661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:01Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0229127508078,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.977121778303186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:13Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.8215591763649,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.630719839920246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 208,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 104,
      "draws": 152,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:13Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.1670799235726,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.01628425017713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.30650400938057,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9868494776583,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.78712902503984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T10:43:48Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.518146546648,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.29690331835047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 102,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:28Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.0281178076189,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.290379711385775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.27287274483318,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 129,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 87,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:22Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.6071390852817,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.207432320938985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:21Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.460996966201,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.11255787082396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:28Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.4002724512168,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.96421938799026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:30Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.512832959456,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.49114002888361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 52.673834544262974,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.2693853856194,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.263089858934286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 37.551153208577354,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:23Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.5119436507632,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.856816919223707,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 90,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0544037106083,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.50702629256417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 26,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 26,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.243599728563,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.880664924292944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 52.475044864937615,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T08:27:58Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9783565501152,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.86715418711666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 57.22830710326107,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.453330167729,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.732078673060073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:01Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9817668716055,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.16636028907312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:31Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9614593543852,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.129670210091273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T10:10:02Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.8799045162689,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.82583876113024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:49:59Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9356837685343,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.3472600456232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:12Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.048658197518,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.292620478258247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 57.22830710326107,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:21Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.8766306909731,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.590043215791468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 52.673834544262974,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 38,
      "draws": 78,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.51206013175,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.225821636295716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 50.75459128937461,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 45,
      "draws": 136,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:23Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.5819924358773,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.616057609593227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 47.16991582857914,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-26T04:32:32Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9467799653128,
      "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.44151957954682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 28,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T04:07:10Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5662249585166,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.58250517714516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-26T03:03:30Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.206661663024,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.49239768223592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 36.39318729849085,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:46Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.8199679947602,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.55197914748385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:44Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.169873719953,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 70.6997686167247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.60765757439077,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:13Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.336443752434,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.855634801012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.361567975806963,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:46Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.4542713590818,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.11245564094769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:48Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.6315145680098,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.43323967778432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.472525230101,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.77411458095119,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T10:36:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4768033532573,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.04373188325387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:00Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.3013243910782,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.89561753299053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:46Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.696901925296,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.736898671389504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:00Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.9046996706184,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.39903902878851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.8549313784958,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.92663955035931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:17Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.729583417106,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.946312445904134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.5904299300091,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.31725364553898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:42Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.9858286719375,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.94334155048709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:48Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.9007927839396,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.456236804374136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.6286930837043,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.414031779727786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T08:40:46Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.4398301501867,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.887127379709426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 46.62023516889464,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:38Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.312238039986,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.42219609913933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:33Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.600072103669,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.921853226556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 41.6303220574653,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:52Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.032997627639,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.730006809943795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T10:25:28Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.8580015094933,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.09912275717949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:47Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.4451277035855,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.279547984289245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-26T04:30:24Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.5662528868663,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.968487196864096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-07-27T10:17:43Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.8208589793223,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.642986122725766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 40.974394715408586,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.0802873129855,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.3681250027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 254,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 127,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:17Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.5578285667934,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.084940854795306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.59154576158009,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.1478710815124,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.08421464409825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 172,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8007026347743,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.65467092606256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.721842944692018,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:50Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.6250464267923,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.28745751743145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 69.22474682633933,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T08:38:42Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.96843152589,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.2543519338834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.2963219883493,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.957262612735185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.3104206683065,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.02260862106261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.6669903963675,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.947553431989036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:34Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.074507007328,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.32514751690616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.288827977848925,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:33Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.8709361070892,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.85378503399073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:47Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.799664295561,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 13.449884255838182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.322614521401,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 91.83061764137966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.2297854950075,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 83.55834325082338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 66,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.2585711313377,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 79.84257508312278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:51Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1683.650875040015,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 77.20302117516688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:02Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.6556396548986,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.15659509023824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.6232412385289,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 73.07850759598226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 43,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.527767943735,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 70.22812208032087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 31.642442208147656,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 34,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.524073532141,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.20962819187783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.07920226560997,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.8608666300522,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.24239570415726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:36Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.0930229588678,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.424425877527234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.828244408040035,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.571475807063,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.49902848103273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T10:41:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.7099847887985,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.51052506806163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.4551680393024,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.57756631923615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:15Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7759859246476,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.498007875599185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.5732183679058,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.32634647961873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 260,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 130,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:16Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.740122695648,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.56433079370909,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26167841562456,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:38Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.7647648288262,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.406674111573565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:36Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.5581163462753,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.43282213007789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T10:46:50Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.4965294796054,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.41858338546655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-26T03:28:35Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.2599469181591,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.68826178338193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.208213223521,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.22582047612717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.542154271933,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.151391350129174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T10:39:35Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.707189128953,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.03021293974064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:16Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.5160558304942,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.88114678411723,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:02Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.6659693492472,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.43999875124963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:58Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.0385830541572,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.17202473580983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:08Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.013744309396,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.35881917136978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:30Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.884883080069,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.60391173446151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:07Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.343401868112,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.35319203148646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:44Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.5529020758545,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.33434993833325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 47.88193642139327,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:16Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.2096633702972,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.66934396725515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:01Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.9567117344586,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.703202638038128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:37Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.265412750451,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.979620323137993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:39Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.3506475607678,
      "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.355022200771856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-26T02:14:14Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.1063201840943,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.523236321771144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 43,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.2973248119208,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.104126773830203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 31.642442208147656,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.285337815342,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 90.82151908302892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.0733020497882,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.961634672591,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 75.98738578456185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:13:39Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.4015620035889,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.09254323204925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.7266168626888,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.28650528900698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 206,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.0601903035,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.10151548866789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.603769221136574,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:48Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.802982390646,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.58294385391025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T08:36:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.041766542292,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.284218510036965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.0640499121846,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.066265662847066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.749923309519133,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:45Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.8705167678413,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.29494455453205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T10:15:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.920523238979,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.25034027872709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:45Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.2842653226814,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.41621180403329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.69173419161021,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:14Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.78268960349,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.355787870899725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.928225102148446,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:46Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.179287904116,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.14134044954261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.630215711361,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.05114074851961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.3871953975538,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.86100001987165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 195,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 195,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.7194140114843,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.586159297967185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.932937500005405,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:45Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.0077416215331,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.68324115546186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:17Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.4607367338915,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.067797325096485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 44.9315472806888,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:08Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.2974094270803,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.66391737325167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.6059977114926,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.20700574081687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.016004726288628,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:19Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.253043117009,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.995121216025154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 36.39318729849085,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:43Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.628492568711,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.2871495944819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-26T01:23:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.9282613982691,
      "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.88368038241504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:03Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.8552075834623,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.89162392193896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9620516903908,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.87578726019612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.979783736733566,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T08:07:41Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.2959606735676,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.35812772742118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 45.462269258808135,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T10:17:46Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.3195981523795,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.03137150213544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 44.9315472806888,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:17Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.5096246302887,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.53812602283009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:10Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3527923761658,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.622454286388646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:14Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0992001492057,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.49197066564704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 39.80145244019624,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.689982844879,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.82251025654144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 233,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-07-27T11:38:30Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.782192176075,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.682571481279417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.353618598248712,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.571115310678,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 17.769416290858764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.801044736378422,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:13Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.0530232290791,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 6.21180309294096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.348522168338,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 5.6844327646508575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 192,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 96,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:21Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1819.9291865090927,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 85.57962471129208,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.532640791940832,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:18Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.30238195533,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 74.41108271929163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:50Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.7828651797977,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.280987550827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:28Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1669.5691004601476,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.23123191335946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.3208067268397,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.84580662581403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-26T05:11:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.9619175578798,
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.27239116238635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:43Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.9180516740412,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.483919215225825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:33Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.5977769607723,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.00561736197007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.288827977848925,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 190,
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 95,
      "draws": 93,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.115041857068,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.10145974217034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.6518151147346,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T10:37:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.409453460546,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.69828421039091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T09:14:03Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.521515251263,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.356162068590265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 44,
      "draws": 81,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:36:31Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7862356855082,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.20997390701733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 32.006220619850886,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T10:03:23Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.8759114421637,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.996350093562853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:44Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.1375092603982,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.75956752250197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 25,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:40Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.0417625819548,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.47922458032685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:20Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3879047496516,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.475476864323102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T10:35:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.9222743715295,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.41687597028761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.6514940291925,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.74641003392749,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 115,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 70,
      "draws": 115,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:11Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8942718475291,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.69893190865684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.68118764215533,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.873384161387,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.035172472656587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:26Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.6488483482228,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.919709973327855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:47Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.5140773232674,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.83423634499792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:47Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.791824430241,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.754628515692527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 188,
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 94,
      "draws": 112,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4570082099108,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.657621512898544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.04868740318581,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:10Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9480224880604,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.15877822959248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 72,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:44Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.9991933165616,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.087039515938308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 46,
      "draws": 83,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:07Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.2618465194205,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.99208014269019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:10Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.8659054082534,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.548654376833127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:37Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.324273248414,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.340296080038364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:14Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.7695118803483,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.19884765587022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 33,
      "draws": 66,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:44Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5413044631157,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.15179482155793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 45.56239790693811,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 71,
      "draws": 93,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.5687072472667,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.04868244275925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.179828253878972,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T11:44:31Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.4738925482284,
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.44814764085012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T11:52:47Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.1341743107275,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.585628377608835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 43.288827977848925,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:59Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.3511651122055,
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 1.8004338185596558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 49.76941398892446,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 684,
      "capped_draws": 48,
      "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": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570124999999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 62.167829720841986,
      "contributing_entrants": null,
      "distinct_rated_opponents": 342,
      "draws": 161,
      "entry_count": 13,
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 170,
      "max_score": 83.50388880910803,
      "measured_at": null,
      "min_score": 48.01330799880638,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 684,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.2407752912268,
      "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"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 59.0230365495569,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8,
      "attempted_matches": 542,
      "capped_draws": 55,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.1598575,
        "mean": 0.093565,
        "median": 0.07461,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7485199999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.995707750614955,
      "contributing_entrants": null,
      "distinct_rated_opponents": 271,
      "draws": 201,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:13Z",
      "losses": 119,
      "max_score": 92.11822076992448,
      "measured_at": null,
      "min_score": 29.006597636421393,
      "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": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.1429759628736,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 52.995707750614955,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 644,
      "capped_draws": 47,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0820533,
        "mean": 0.0699502125,
        "median": 0.06609614999999999,
        "min": 0.0587988,
        "recorded_attempt_count": 17,
        "run_count": 16,
        "total": 1.1192034
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 50.22774359214498,
      "contributing_entrants": null,
      "distinct_rated_opponents": 322,
      "draws": 305,
      "entry_count": 27,
      "failed_game_aliases": [],
      "first_pass_admitted": 15,
      "first_pass_rate": 0.9375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:01:47Z",
      "losses": 257,
      "max_score": 67.27022799576758,
      "measured_at": null,
      "min_score": 26.07854941714752,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 644,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.8511208571324,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 50.22774359214498,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 444
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 500,
      "capped_draws": 56,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.97393
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.14570999192436,
      "contributing_entrants": null,
      "distinct_rated_opponents": 250,
      "draws": 174,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:35Z",
      "losses": 146,
      "max_score": 59.15070675443215,
      "measured_at": null,
      "min_score": 35.18281284883366,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 500,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.5505511671608,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 47.14570999192436,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 636,
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "max": 0.116343,
        "mean": 0.07787519999999999,
        "median": 0.0843883,
        "min": 0.041110400000000005,
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 1.2460032
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 46.61900356772293,
      "contributing_entrants": null,
      "distinct_rated_opponents": 318,
      "draws": 326,
      "entry_count": 28,
      "failed_game_aliases": [],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 258,
      "max_score": 76.23053193535173,
      "measured_at": null,
      "min_score": 20.684453538846107,
      "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": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.8256477101834,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": 11,
      "repaired_rate": 0.6875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.61900356772293,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 406
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 448,
      "capped_draws": 16,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.262825
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.38943024530096,
      "contributing_entrants": null,
      "distinct_rated_opponents": 224,
      "draws": 112,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:41Z",
      "losses": 147,
      "max_score": 62.93013963759991,
      "measured_at": null,
      "min_score": 28.832423610551896,
      "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": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.571681633783,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.83355042960994,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 528,
      "capped_draws": 30,
      "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": 0.121464375,
        "median": 0.124865,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.0694849999999998
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 47.16916339303791,
      "contributing_entrants": null,
      "distinct_rated_opponents": 264,
      "draws": 149,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:56:29Z",
      "losses": 177,
      "max_score": 59.90860829604776,
      "measured_at": null,
      "min_score": 32.11930845299747,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 528,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.1348386309048,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.8004814112764,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 446,
      "capped_draws": 73,
      "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": 0.0216425,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.0701532764951,
      "contributing_entrants": null,
      "distinct_rated_opponents": 223,
      "draws": 163,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:01:47Z",
      "losses": 142,
      "max_score": 80.99600365638999,
      "measured_at": null,
      "min_score": 29.95785357363107,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 446,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.7971729058434,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 44.557587685019186,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 782,
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.00223773125,
        "median": 0.00220356,
        "min": 0.00093502,
        "recorded_attempt_count": 23,
        "run_count": 14,
        "total": 0.030659259999999997
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 45.96433865838611,
      "contributing_entrants": null,
      "distinct_rated_opponents": 391,
      "draws": 255,
      "entry_count": 12,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.42857142857142855,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:28Z",
      "losses": 267,
      "max_score": 58.47714496936588,
      "measured_at": null,
      "min_score": 23.58388507203711,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 782,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6217233416023,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.42857142857142855,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 44.226677896070974,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 260
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 534,
      "capped_draws": 86,
      "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-2026-07-25": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063374999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.74920947025871,
      "contributing_entrants": null,
      "distinct_rated_opponents": 266,
      "draws": 235,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T16:02:00Z",
      "losses": 162,
      "max_score": 56.98896235225361,
      "measured_at": null,
      "min_score": 27.543654388822937,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 534,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.3895713118704,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.47976243302143,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": 1090,
      "capped_draws": 159,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.004834030033333333,
        "mean": 0.0027724950333333333,
        "median": 0.0022439992166666664,
        "min": 0.00169122,
        "recorded_attempt_count": 35,
        "run_count": 24,
        "total": 0.06653988079999999
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 45.06881836311115,
      "contributing_entrants": null,
      "distinct_rated_opponents": 545,
      "draws": 334,
      "entry_count": 17,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 412,
      "max_score": 47.38658897369575,
      "measured_at": null,
      "min_score": 40.46122645082023,
      "model_code_failure_rate": 0.2916666666666667,
      "model_code_failures": 7,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7083333333333334,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1090,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.314911503901,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333337,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.34619909670711,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 344
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 454,
      "capped_draws": 110,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.48343610226164,
      "contributing_entrants": null,
      "distinct_rated_opponents": 226,
      "draws": 244,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:24Z",
      "losses": 99,
      "max_score": 56.42732881438667,
      "measured_at": null,
      "min_score": 27.049679476012503,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.5841541841166,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.08862885535952,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 408,
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.02955606902857143,
        "median": 0.0063034062,
        "min": 0.0057139812,
        "recorded_attempt_count": 10,
        "run_count": 7,
        "total": 0.2068924832
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 41.81697003012698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 204,
      "draws": 113,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 151,
      "max_score": 67.54305795364324,
      "measured_at": null,
      "min_score": 28.65315269754207,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.7333897226706,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.23609863849646,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0148808,
        "mean": 0.0114004875,
        "median": 0.01124825,
        "min": 0.00845595,
        "recorded_attempt_count": 23,
        "run_count": 16,
        "total": 0.1824078
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 39.95432300929791,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 228,
      "entry_count": 15,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:18:59Z",
      "losses": 202,
      "max_score": 65.72298874215366,
      "measured_at": null,
      "min_score": 14.65937731419278,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.2283589294589,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 39.3148475023505,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 474,
      "capped_draws": 87,
      "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": 0.015562441375,
        "median": 0.0131167185,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.124499531
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.04782157796235,
      "contributing_entrants": null,
      "distinct_rated_opponents": 236,
      "draws": 159,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:14Z",
      "losses": 161,
      "max_score": 76.1429991599217,
      "measured_at": null,
      "min_score": 20.61584059577335,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.8800202747846,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.73297991531701,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "max": 0.058529250000000005,
        "mean": 0.03888066562499999,
        "median": 0.038104875,
        "min": 0.029012250000000003,
        "recorded_attempt_count": 20,
        "run_count": 16,
        "total": 0.6220906500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.663748074092574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 272,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:19:02Z",
      "losses": 208,
      "max_score": 58.83351636895526,
      "measured_at": null,
      "min_score": 24.01162765730244,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.085554722274,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.663748074092574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 404,
      "capped_draws": 22,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 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": 41.537281009126794,
      "contributing_entrants": null,
      "distinct_rated_opponents": 202,
      "draws": 105,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:23Z",
      "losses": 143,
      "max_score": 53.01828026826074,
      "measured_at": null,
      "min_score": 27.705611244015376,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.75,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.1982821115696,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.654795540982754,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 314,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 13
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.136952,
        "mean": 0.07424775,
        "median": 0.070604,
        "min": 0.041758,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13
        },
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.593982
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.5280618812843,
      "contributing_entrants": null,
      "distinct_rated_opponents": 156,
      "draws": 103,
      "entry_count": 12,
      "failed_game_aliases": [],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:54:23Z",
      "losses": 102,
      "max_score": 86.61766309589059,
      "measured_at": null,
      "min_score": 18.13272808568275,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "O3",
      "model_slug": "o3",
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.5044579634953,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.5280618812843,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 434,
      "capped_draws": 80,
      "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": 39.08501586962297,
      "contributing_entrants": null,
      "distinct_rated_opponents": 217,
      "draws": 200,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:31Z",
      "losses": 119,
      "max_score": 72.6465473220185,
      "measured_at": null,
      "min_score": 26.272777344588157,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.5637183271122,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 36.37270568635381,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 914,
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.014209038,
        "mean": 0.0093957345,
        "median": 0.009312405,
        "min": 0.004429524000000001,
        "recorded_attempt_count": 25,
        "run_count": 16,
        "total": 0.150331752
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.70527307375653,
      "contributing_entrants": null,
      "distinct_rated_opponents": 457,
      "draws": 314,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:46Z",
      "losses": 351,
      "max_score": 52.54958566492595,
      "measured_at": null,
      "min_score": 23.22225700698019,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 914,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.8553869792495,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.50017326121874,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 296,
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.0260953,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.51873040253819,
      "contributing_entrants": null,
      "distinct_rated_opponents": 148,
      "draws": 83,
      "entry_count": 7,
      "failed_game_aliases": [
        "GB2-02"
      ],
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:43Z",
      "losses": 123,
      "max_score": 49.72936122718848,
      "measured_at": null,
      "min_score": 19.57553453515884,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.875,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.4001767574143,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.31975511978292,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 750,
      "capped_draws": 72,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.053540475,
        "mean": 0.026315053125,
        "median": 0.024512850000000003,
        "min": 0.012912625,
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 0.4210408500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.93587026592818,
      "contributing_entrants": null,
      "distinct_rated_opponents": 375,
      "draws": 252,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 307,
      "max_score": 50.09192000149523,
      "measured_at": null,
      "min_score": 26.63272439732407,
      "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": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.7292460924964,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.37270034463752,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 1564,
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 29
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.021615250000000003,
        "mean": 0.017288937500000004,
        "median": 0.01830825,
        "min": 0.01259225,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 29
        },
        "run_count": 24,
        "token_priced_attempt_count": 29,
        "total": 0.4149345
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 33.80666922295059,
      "contributing_entrants": null,
      "distinct_rated_opponents": 780,
      "draws": 631,
      "entry_count": 24,
      "failed_game_aliases": [],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.7916666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 549,
      "max_score": 50.38643236051798,
      "measured_at": null,
      "min_score": 21.486420364689437,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1564,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.7509540537976,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333337,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 33.80666922295059,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 384
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 324,
      "capped_draws": 45,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0032939400000000004,
        "mean": 0.0016413085,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.591515338160217,
      "contributing_entrants": null,
      "distinct_rated_opponents": 162,
      "draws": 121,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 123,
      "max_score": 49.8631353550523,
      "measured_at": null,
      "min_score": 11.042241208882738,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.316982892477,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.591515338160217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 366,
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00391754,
        "mean": 0.0023617857142857143,
        "median": 0.00186618,
        "min": 0.00144036,
        "recorded_attempt_count": 8,
        "run_count": 7,
        "total": 0.0165325
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 32.14193352522236,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 106,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:06:56Z",
      "losses": 152,
      "max_score": 44.39699646208931,
      "measured_at": null,
      "min_score": 22.18853644184757,
      "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": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.1527338375363,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.926822455599037,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 1646,
      "capped_draws": 263,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 56
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 7,
        "max": 0.013223525,
        "mean": 0.0089983359375,
        "median": 0.00845865,
        "min": 0.0058062875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 56
        },
        "run_count": 32,
        "token_priced_attempt_count": 56,
        "total": 0.28794675000000003
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 32.52979168045882,
      "contributing_entrants": null,
      "distinct_rated_opponents": 823,
      "draws": 638,
      "entry_count": 25,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 589,
      "max_score": 36.65857398163143,
      "measured_at": null,
      "min_score": 28.45383607650836,
      "model_code_failure_rate": 0.21875,
      "model_code_failures": 7,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.78125,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1646,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.5660707930397,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 15,
      "repaired_rate": 0.46875,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.58290880274737,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 419
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 1246,
      "capped_draws": 189,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0027823742,
        "mean": 0.0022230800541666665,
        "median": 0.002112839,
        "min": 0.001825724,
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 0.0533539213
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 32.04826272157318,
      "contributing_entrants": null,
      "distinct_rated_opponents": 623,
      "draws": 506,
      "entry_count": 19,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5833333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 455,
      "max_score": 38.39386082118144,
      "measured_at": null,
      "min_score": 25.35335800760461,
      "model_code_failure_rate": 0.20833333333333337,
      "model_code_failures": 5,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.7916666666666666,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1246,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.778886436927,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333337,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 30.23013467663233,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 285
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 374,
      "capped_draws": 18,
      "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": 0.08145696
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 30.97000026471277,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 116,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:58:41Z",
      "losses": 163,
      "max_score": 36.47987858051721,
      "measured_at": null,
      "min_score": 17.078759313374523,
      "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": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.9665230506514,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.98455429099188,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 618,
      "capped_draws": 149,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 28.769437863151424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 309,
      "draws": 305,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 223,
      "max_score": 44.48159231995547,
      "measured_at": null,
      "min_score": 18.886821253244385,
      "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": 618,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.2087654477366,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": 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"
      },
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 25.58004949521818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 490,
      "capped_draws": 73,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.17574199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.58929565473188,
      "contributing_entrants": null,
      "distinct_rated_opponents": 245,
      "draws": 204,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:56:04Z",
      "losses": 220,
      "max_score": 42.723936908981315,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 489,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.120605397401,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 23.58929565473188,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 340,
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 138,
      "entry_count": 8,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:46:59Z",
      "losses": 100,
      "max_score": 55.113612498782416,
      "measured_at": null,
      "min_score": 25.620538806917818,
      "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": "provisional",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9656335191942,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.73044836931286,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 1188,
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 594,
      "draws": 342,
      "entry_count": 28,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:40Z",
      "losses": 435,
      "max_score": 54.02396836927419,
      "measured_at": null,
      "min_score": 26.01512692587781,
      "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": "provisional",
      "rated_matches": 1188,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8590454079178,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 40.05094350246561,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 411
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 342,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 102,
      "entry_count": 8,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:10Z",
      "losses": 132,
      "max_score": 56.36684029870736,
      "measured_at": null,
      "min_score": 22.30259680139711,
      "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": "provisional",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1314133867284,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.70475670619771,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 438,
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.2156775,
        "mean": 0.157461515625,
        "median": 0.15705206249999998,
        "min": 0.098579625,
        "recorded_attempt_count": 33,
        "run_count": 16,
        "total": 2.51938425
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 46.31080487287338,
      "contributing_entrants": null,
      "distinct_rated_opponents": 218,
      "draws": 181,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 139,
      "max_score": 69.71683172233598,
      "measured_at": null,
      "min_score": 26.222888398882304,
      "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": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.1656686637784,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.66403487978772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 298,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 149,
      "draws": 98,
      "entry_count": 7,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:51:15Z",
      "losses": 114,
      "max_score": 53.57169863410424,
      "measured_at": null,
      "min_score": 21.20665469801167,
      "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": "provisional",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.0615511034816,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 35.68218931552467,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 284,
      "capped_draws": 59,
      "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": 0.0429946875,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.67062590477188,
      "contributing_entrants": null,
      "distinct_rated_opponents": 141,
      "draws": 64,
      "entry_count": 4,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T16:02:00Z",
      "losses": 130,
      "max_score": 38.2909369413615,
      "measured_at": null,
      "min_score": 26.072194902063597,
      "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": 281,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.4837759080667,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.472612207417814,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 3,
      "wins": 87
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 218,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 58,
      "entry_count": 5,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:31Z",
      "losses": 111,
      "max_score": 41.40382647576317,
      "measured_at": null,
      "min_score": 0.0,
      "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": "provisional",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.9966234633323,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 23.538864797348666,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 344,
      "capped_draws": 116,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.02527583517874,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 116,
      "entry_count": 5,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:05Z",
      "losses": 164,
      "max_score": 27.522770043194065,
      "measured_at": null,
      "min_score": 26.527781627163417,
      "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": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.4107181713196,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 20.20610664115091,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:32Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1840.8511544908365,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 92.11822076992448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:37Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.569380601013,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.6465473220185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.3589534729288,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.57544686267458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:26Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.388491274526,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.484582777796334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:46Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.2591240187812,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.47714496936588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 42,
      "draws": 69,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:41Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.9822709107812,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.62451221481294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.111817092302566,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 16,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:28:50Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.4332627403917,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.22022924708464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:15Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.1781720591457,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.98896235225361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.6962238815845,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.894074601780616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:45Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.0858652952545,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.36684029870736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 42,
      "draws": 67,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:14Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.8684946102,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.03078053724524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.111817092302566,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:03Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.340614191469,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.81582799890011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:18Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.6926849361364,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.57169863410424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:25:02Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.8471484037084,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.06691150878728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-26T05:08:25Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.8238828088404,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.02997089758741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 62,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:40Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.1257108359016,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.79163908116498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 28,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:06Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.425377493292,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.636647445449704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 220,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 110,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.600222806797,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.38658897369575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.375101550890244,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:35Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.438796086254,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.374389594950806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:46Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.1795477973849,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.521519400812174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.928225102148446,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:00:39Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9655056194315,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.52251713937394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.5771573742084,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.48159231995547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.5007886172232,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.39699646208931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 184,
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 92,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:40Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.8955897479009,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.215606466401034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.232085339282207,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:10Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.7292262906526,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.909739239921585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:35Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.0631482289907,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.23843353793476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:15Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0064719759512,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.837923897204504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:45Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.0798296671542,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.007186117752184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 270,
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 135,
      "draws": 78,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.3174388329098,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.65857398163143,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.763148331401503,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 220,
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 110,
      "draws": 70,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:48Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8409082389398,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.58749680418459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.356468484757592,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:06Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.142971092423,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.8499002021569,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 3,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:34Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.3232146087823,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.87536426896172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:34Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.448577341908,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.896390308583022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:28:50Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.552660186412,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.32612813598716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:40Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.5463193317332,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.522770043194065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.606750070474943,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T16:06:56Z",
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.163404047537,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.63272439732407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T08:33:33Z",
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.399703918666,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.974404110127313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.3314720438675,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.80363707825724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:04Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4621431048597,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.18281284883366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 68,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T14:52:06Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.6155054033272,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.962548767694756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:15Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8766895584683,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.97531310705538,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:06Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.5716831996058,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.61416074557098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:01Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.383120170803,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.60246582139271,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 88,
      "draws": 168,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:05Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.668846160256,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.22481911643467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.00449926204939,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 119,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T14:52:08Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9605922249866,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.72052116086004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.259682442018587,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3686744490708,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.37203516308192,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.7746335763547,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.56362733585045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:05Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.1855742024472,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.406715690809293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 62,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.2182531123694,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.0661415287832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4728086634052,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.40359272291873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:14Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.3396386261843,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.041029137757743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.955126495349,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.936859423853782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:04Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0802986534875,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.832423610551896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5798481424442,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.82265996372679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 60,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:34Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5865175875335,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.71454218394329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 56,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T10:49:51Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.3293696473902,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.65315269754207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 234,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 117,
      "draws": 216,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:13Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.9194358272002,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.45383607650836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.29857046522331,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:02Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9611713998297,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.705611244015376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 60,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:28Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.6963835500655,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.360571887099717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 62,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:23:51Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.8989139702087,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.272777344588157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 76,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-26T01:22:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0646296592502,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.237099338958902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 47,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:06Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4715871938947,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.222888398882304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.175080615072,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.085553048269652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 39,
      "draws": 112,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:13Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.9731336346329,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.07854941714752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 50.052677204897826,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-26T02:16:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3188858458,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.059066298254493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 57,
      "draws": 103,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.716589613089,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.01512692587781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T09:04:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.0637410889549,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.620538806917818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 18,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5847832126149,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.85962983613944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3741079493293,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.69204681390362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 40,
      "draws": 113,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:23:51Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.518205022639,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.54265599085522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 49.4839229723041,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 68,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 34,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.3300278167235,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.45308478035796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.90444889821687,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:55Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.920108094656,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.08227965708637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-26T04:32:18Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.3665103598798,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.09081208170358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.092140040724,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.1033903036507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:59Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.5793891002238,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.01828026826074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:26Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.1619524841408,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.688836210667226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:40Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.1875388618716,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.412762414887055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-26T04:27:36Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.381974984623,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.32372030022173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 156,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 78,
      "draws": 96,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.103686313155,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.38643236051798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 25.02849041872271,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 49,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.9087960092234,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.09192000149523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.97128781498596,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 41,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1810017274283,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.94286785536366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.41808305530269,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:36Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.648010167357,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.72936122718848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:20Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.356600835827,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.43891826866166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 46.05265101338746,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T14:55:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.323955650604,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.38385520211626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:04Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.7556987902174,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.10653317662637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T09:13:01Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.9188274128549,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.723936908981315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2660520172667,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.495274622791904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 51,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:30Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6623509478843,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.985067425141104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 25.597143087872503,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:18Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.092226074721,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.56307486091444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.51728889973289,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 18,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.5326664526883,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.2217430159087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 180,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 90,
      "draws": 66,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:13Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.958429102522,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.82859840268824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.65033652638543,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:59Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.2674122393996,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.461208791388664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 24,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T14:53:14Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.0101184596929,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.16178607693494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.381307433771,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.64090722117748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 92,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 46,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.018589518323,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.38298276714462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 45.13137666820794,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:11Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.666473249807,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.4921765950404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.304426701457977,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 31,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:50:00Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.1096514863327,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.38334591324993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 30,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 15,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:31:27Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 30,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.179191434123,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.055991271142776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 46.05265101338746,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:51Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.0705798788915,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.48358424139654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:07Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2608906471414,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.440225048579062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 70.38271273642583,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 78,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 39,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.9156680808603,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.684453538846107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 35.295968555715895,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:21Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.207385463267,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.61584059577335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:17Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.1896956500836,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.655504012060575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 54,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:35Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.2912045583273,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.01330799880638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.70344991379835,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:55Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.367240999507,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.06024334765576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 71,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:06Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.0291620852558,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.465613636603344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 14,
      "draws": 16,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:39Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.8999918600214,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.70878194898091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 49.09766908852594,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T14:55:10Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.129620533277,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.60853817575416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:59Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.558199870668,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.42523001417078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.95048007367414,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 37,
      "draws": 75,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.109269958217,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.848221051862794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.76160072203399,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.5933624248837,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.697311929291594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:43Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.700299003465,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.564843479998515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:38Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7518112619032,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.47987858051721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.4916414654292,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.004894996193826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:52:49Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.1061108254105,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.99123440741221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 11
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 158,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 79,
      "draws": 112,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:32Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.409438596447,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.711020849728605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.83117993386317,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 55,
      "draws": 90,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:56Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.4317047269096,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.188797475282726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.137368732378228,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:08Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.0471982021531,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.22189995892514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 92,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:40Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.696435624508,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.74918488008487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:40Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2296172501635,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.4691324962955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9339395098796,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.30566532198333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 39,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:33Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.9701197438192,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.22275482443267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 190,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 95,
      "draws": 139,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8175269280712,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.17685443336674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.77768935251636,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:06Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.4876650964738,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.11930845299747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 56,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:23Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5058004589516,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.642255258124266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 82,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.7594087580565,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.443391993025433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.08718040460786,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 66,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.404391708064,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.815219490526346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 17,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:38Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.8102858634056,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.274656356852365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 40.76542547285167,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 176,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 88,
      "draws": 149,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:53Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.8644480597122,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.36600328835098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.53736994289201,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 90,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:49:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9312245396438,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.264406825032907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 53.555037320705495,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 17,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-26T22:08:31Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.143974925331,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.956096391857447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 40.76542547285167,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 24,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 12,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:45:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.6541457347726,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 11.042241208882738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 56.25,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:49Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1823.6955807261916,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 83.50388880910803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1752.4021108928348,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.1510189524612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:36Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.6046296590218,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.925284579574985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.928056527532547,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:26Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.385772117564,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.86232872007845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:32:35Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.5434120737496,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.42732881438667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:15Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.708544050022,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.863348614056285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:14Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.229860059093,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.829711260628585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 48.946042395649414,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:28Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8298949184382,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.31323520003257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.0274446215944,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.38845226238323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.2272824362703,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.261687320285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:15Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.701516438078,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.983757275316115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.0252991014984,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.41155335314362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.300442572851765,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:14Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.516113452013,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.97799867637564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T15:07:01Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.8308552065046,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.99990230008747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:13Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.412712328678,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.43956011342773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 66.24964258315117,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.8515472914996,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.575444671868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 204,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:08Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.2102640235487,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.46122645082023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 101
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 192,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 96,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.9972224389992,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.8544724665147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.6221436835365,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.39386082118144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.361567975806963,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.928615167466,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.2909369413615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:59Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.5767315502376,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.35580390238191,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T15:00:38Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.093697253425,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.28769585919104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:17Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.244405392198,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.48079904046824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.501367016649,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.69618438144857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:00Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8102664408416,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.13361761793311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.3905933062547,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.3847722466155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 202,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 101,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:14Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.7739734730787,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.101312271875415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.913911453098134,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.5945266252224,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.9170413033881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.7941697138317,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.12678637185235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:51:12Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.63995352344,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.39821775319491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 210,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 105,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.07449543575,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.279090243345703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.74831355425182,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.099984749541,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.22225700698019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:30:45Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.022394286137,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.18853644184757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.6134001853593,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.379233976999053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:58Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.3323160300529,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 14.65937731419278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1106.586721726533,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:36Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.1459218022244,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 89.13691320039523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 18,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:44Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1768.0118763760397,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 86.61766309589059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:32Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1674.832336171311,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.1429991599217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.165952256158,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 71.14412736694287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 43,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T16:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.421943677852,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.27022799576758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.01679293279406,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.6186674821492,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.09200456336322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 188,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 94,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.6253544498152,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.00481551608911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.9490803264906,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:41Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.7733406383302,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.83012501610077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:39Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.184208348665,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.62283719668116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:56Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.0097462451129,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.54958566492595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:18Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.0471700351973,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.53892965023924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 38,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.5653877312857,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.643221073026574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 51.74125868734754,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.406710872713,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.8631353550523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.0980280128524,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.2174811242672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 182,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:32Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.631257835851,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.35863966481747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.127117585218937,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.7533405191086,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.279690469131054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 168,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 84,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.883227109784,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.40962689886413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:21Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3056015259317,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.684186833033415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-07-27T11:59:44Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.6038581939165,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.45601398414009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:25:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8254161871469,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.40382647576317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.6574813704308,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.796634638618634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.487204134739892,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:42Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.6201022386813,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.16937604000977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.4473281980904,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.31788335875319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:48Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.7430753287372,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.249112314196054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-07-26T02:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.0664771587387,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.84809500658452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:41Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.5858526769046,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.63163240739917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:36Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.579754559503,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.49761345604342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:58:43Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.2957907129323,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.401527305050784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T16:01:47Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.8150715027673,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.547572564793132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.3542233252822,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.469471573505537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.3201234614855,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.43111022257915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:00Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.76180671258,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.335737306568312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.9692131063861,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1243.4193512828674,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.886821253244385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-27T15:14:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1174.1929957595082,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 9.219198794244829,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.2492100095503,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.99600365638999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:25Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.0788730945349,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 78.56920080122724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1730.0831070176853,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.23053193535173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.50491251305893,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:20Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.1651313142668,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.71683172233598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:24Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.249574240341,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.54305795364324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-26T05:17:45Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.62727187213,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.72298874215366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.007726186437235,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:20Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.8782657464328,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.93013963759991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.027897449992,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.90860829604776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.8243127331189,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.83351636895526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 31.007726186437235,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:22Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.596224581565,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.113612498782416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 70,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-07-27T16:02:40Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.4031788330378,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.02396836927419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 28.68118764215533,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:26Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5834431296869,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.462360625353874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:10Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.3262272831655,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.944407671620375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:10:13Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7496459810498,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.45212194783904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:14Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.8456094590335,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.82415975623741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:24Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.9750388104458,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.899176885906776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.3127110418286,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.96115933902756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:23Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.3423615846004,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.873011049349245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2235891986847,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.50337610769172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 48.73444152250164,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:13Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8610596627066,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.3880018617899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 216,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.985570579499,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.07982876915568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.814596123589618,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:20Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.2743046740543,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.55977304408127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.5863858748698,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.620804135772225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.570138866854082,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.3110822405563,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.10621141460972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.74936409813348,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T15:54:23Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4098434956095,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.55029327378088,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 64.59124787447364,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.7423245669345,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.35976589284266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:13Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.3333503741408,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.908555878820593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:48Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.4160981986215,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.66929794584434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T15:10:12Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.8159516092887,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.816413152201964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:05Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.1995227607265,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.527781627163417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 192,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 94,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.983665204464,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.486420364689437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.282056102542683,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T10:36:04Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.8016849909914,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.20665469801167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.5505253206957,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 17.078759313374523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.8599986467784,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 13.7890857228278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:40Z",
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1134.1894705301404,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 40,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:03Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.3794583194792,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 67.13253570322934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 33.15312037953302,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T15:19:58Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.365116897373,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.99415499988833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.4486548697253,
      "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.15070675443215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:24Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.5524233506335,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.934388839397826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 40,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:03Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.277878301726,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.712424267511985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 50.2932617637271,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:29Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.8431949043122,
      "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.853328871691126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 70,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.5485274057612,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.79474327591976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 28.68118764215533,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 7,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:16Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.6287669745502,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.55996968426065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:29Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.549910317883,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.44282331296946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 292,
      "capped_draws": 184,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 146,
      "draws": 184,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:09Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.3505911967395,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.476964983236684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.393742914134872,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 49,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1357275132184,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.95785357363107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 74,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:46Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.5903871925957,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.006597636421393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T10:42:50Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.1797497732612,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.903404995054014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.4863124214994,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.305825631962907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 59,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:34Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.9523521591466,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.090589774286613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 55,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.099914328351,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.543654388822937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 40,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3787650864267,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.40244569391851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T14:50:07Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9671606777888,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.049679476012503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5298755363042,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.69416926616589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 53,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:40Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.1437448693234,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.58497915083693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:30Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.104133950512,
      "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": "omitted",
          "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": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.12237999875593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 53,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:39:59Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.5092940470956,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.072194902063597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 45,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:34Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.727549023724,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.811146558890066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 148,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:11Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.161544741987,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.69338379391731,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.220668586617483,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 208,
      "capped_draws": 160,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 104,
      "draws": 160,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:30Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.5055080741283,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.35335800760461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.898126228636851,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 115,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "draws": 115,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:06Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.3637798159552,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.05809791299054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.606750070474943,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "draws": 113,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:12Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9833201414342,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": 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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.225753638009312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.606750070474943,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 57,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:08Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.5832665791972,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.01162765730244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T14:49:23Z",
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.1465689714887,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.944071579260378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 119,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:07Z",
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.85097822939,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.58388507203711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.377800258513927,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 29,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:01Z",
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.0774072462827,
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.30259680139711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.26400420140049,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 63,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:45Z",
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.4353933526995,
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.513590194658597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 103,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 103,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:01Z",
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.9721409206004,
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.416862714154615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:21Z",
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.907367827263,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.57553453515884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 20,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.816045493821,
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.13272808568275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 67.16844047215152,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 466,
      "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-2026-07-25": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.66097
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.47120747309498,
      "contributing_entrants": null,
      "distinct_rated_opponents": 233,
      "draws": 66,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:20:16Z",
      "losses": 80,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 61.39391405879897,
      "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": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1732.6539292122177,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 83.47120747309498,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 320
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 520,
      "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": 1.320515,
        "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": 77.51610158816355,
      "contributing_entrants": null,
      "distinct_rated_opponents": 260,
      "draws": 40,
      "entry_count": 13,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:19:34Z",
      "losses": 100,
      "max_score": 99.01750849232472,
      "measured_at": null,
      "min_score": 63.475663086016624,
      "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": 520,
      "rating_method": "sequential_elo",
      "raw_elo": 1759.0864439224283,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 73.59490781264122,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 380
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 486,
      "capped_draws": 22,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.140645
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 71.87937601763771,
      "contributing_entrants": null,
      "distinct_rated_opponents": 243,
      "draws": 101,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:53:35Z",
      "losses": 87,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 38.82631568621353,
      "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": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1707.4052727023304,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 71.87937601763771,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 298
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 434,
      "capped_draws": 30,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.15184887212625,
      "contributing_entrants": null,
      "distinct_rated_opponents": 217,
      "draws": 98,
      "entry_count": 7,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:29:49Z",
      "losses": 94,
      "max_score": 88.02796582947613,
      "measured_at": null,
      "min_score": 30.921753926830576,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 433,
      "rating_method": "sequential_elo",
      "raw_elo": 1680.483773314538,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 65.91430169096594,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8,
      "attempted_matches": 490,
      "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-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 80.47395
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 65.28432384240854,
      "contributing_entrants": null,
      "distinct_rated_opponents": 245,
      "draws": 59,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:17:28Z",
      "losses": 138,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 15.99986870925893,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.6753266447145,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 65.28432384240854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 293
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 496,
      "capped_draws": 22,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.13752,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.32801249999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.919234658332655,
      "contributing_entrants": null,
      "distinct_rated_opponents": 248,
      "draws": 97,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:55:10Z",
      "losses": 169,
      "max_score": 72.0322843616957,
      "measured_at": null,
      "min_score": 43.85247714738262,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.7047709144026,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 54.919234658332655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 472,
      "capped_draws": 7,
      "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-2026-07-25": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 28.806541000000003
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 51.9216378429439,
      "contributing_entrants": null,
      "distinct_rated_opponents": 236,
      "draws": 132,
      "entry_count": 8,
      "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
      },
      "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": "2026-07-27T15:56:30Z",
      "losses": 155,
      "max_score": 76.4748305783871,
      "measured_at": null,
      "min_score": 28.146372762679754,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.1347318400751,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 50.415055892633696,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 20,
      "attempted_matches": 716,
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.1445437333333333,
        "mean": 0.08818255,
        "median": 0.07401653333333333,
        "min": 0.052337466666666665,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 2.1163812
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": 51.68224842902943,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 261,
      "entry_count": 40,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 12,
      "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
      },
      "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": "2026-07-27T15:57:47Z",
      "losses": 479,
      "max_score": 64.73590439615545,
      "measured_at": null,
      "min_score": 22.82665639057853,
      "model_code_failure_rate": 0.16666666666666666,
      "model_code_failures": 4,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 0.8333333333333334,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 716,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.1231601642353,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": 8,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 49.37943174643163,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 698
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 422,
      "capped_draws": 6,
      "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-2026-07-25": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.44989
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.53327801033048,
      "contributing_entrants": null,
      "distinct_rated_opponents": 211,
      "draws": 59,
      "entry_count": 7,
      "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
      },
      "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": "2026-07-27T11:53:30Z",
      "losses": 123,
      "max_score": 50.53327801033048,
      "measured_at": null,
      "min_score": 50.53327801033048,
      "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": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.7804147256502,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 48.87418004544679,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 240
    },
    {
      "admitted_plugins": 18,
      "attempted_matches": 725,
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 18,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.9392418,
        "mean": 0.7382814249999998,
        "median": 0.7264120999999999,
        "min": 0.4980382,
        "recorded_attempt_count": 48,
        "run_count": 23,
        "total": 16.779512399999994
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": 50.681284389884866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 363,
      "draws": 412,
      "entry_count": 36,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:54:18Z",
      "losses": 407,
      "max_score": 53.42069139868415,
      "measured_at": null,
      "min_score": 46.17117874326892,
      "model_code_failure_rate": 0.21739130434782608,
      "model_code_failures": 5,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.782608695652174,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 725,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.933390281058,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": 18,
      "repaired_rate": 0.782608695652174,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 47.668751755366614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 528
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 768,
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 7,
        "cost_basis_counts": {
          "local_standard_estimate": 15
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.5164726249999998,
        "mean": 1.0182428035714286,
        "median": 0.9670455,
        "min": 0.8356068750000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 15
        },
        "run_count": 12,
        "token_priced_attempt_count": 15,
        "total": 12.214044
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 46.85603201539517,
      "contributing_entrants": null,
      "distinct_rated_opponents": 384,
      "draws": 207,
      "entry_count": 12,
      "failed_game_aliases": [],
      "first_pass_admitted": 10,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:59:11Z",
      "losses": 271,
      "max_score": 66.08919562986975,
      "measured_at": null,
      "min_score": 28.93961926553232,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 768,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.0200419973128,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 46.85603201539517,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 626,
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4567,
        "mean": 0.3660333333333334,
        "median": 0.355077,
        "min": 0.234622,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-07-25": 8
        },
        "run_count": 10,
        "token_priced_attempt_count": 10,
        "total": 3.5443079999999996
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 45.05500396335153,
      "contributing_entrants": null,
      "distinct_rated_opponents": 313,
      "draws": 195,
      "entry_count": 10,
      "failed_game_aliases": [],
      "first_pass_admitted": 10,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 18,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:56:30Z",
      "losses": 219,
      "max_score": 59.06172320072071,
      "measured_at": null,
      "min_score": 31.45351907819096,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7968903732362,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.05500396335153,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 212
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 384,
      "capped_draws": 66,
      "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": 45.85533896437726,
      "contributing_entrants": null,
      "distinct_rated_opponents": 192,
      "draws": 90,
      "entry_count": 6,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:53:51Z",
      "losses": 144,
      "max_score": 76.6585459712308,
      "measured_at": null,
      "min_score": 23.27152769675579,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 384,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.248635605296,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.67320125602332,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 294,
      "capped_draws": 35,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.454645,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.15278157179898,
      "contributing_entrants": null,
      "distinct_rated_opponents": 147,
      "draws": 168,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:45Z",
      "losses": 174,
      "max_score": 62.786908880400794,
      "measured_at": null,
      "min_score": 24.57930679395035,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 293,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.4392846428914,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 42.15278157179898,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 183
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 961,
      "capped_draws": 148,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.38568888333333334,
        "mean": 0.29249454166666666,
        "median": 0.2834616125,
        "min": 0.2238526,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 25
        },
        "run_count": 17,
        "token_priced_attempt_count": 25,
        "total": 5.07700365
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": 42.36624656479914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 481,
      "draws": 320,
      "entry_count": 15,
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.5882352941176471,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 9,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:57:49Z",
      "losses": 340,
      "max_score": 42.36624656479914,
      "measured_at": null,
      "min_score": 42.36624656479914,
      "model_code_failure_rate": 0.1176470588235294,
      "model_code_failures": 2,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.8823529411764706,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 961,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9236744831069,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.29411764705882354,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 41.0610994492053,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 301
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 200,
      "capped_draws": 25,
      "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": 0.4890770625000001,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.912616499999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.533353004955416,
      "contributing_entrants": null,
      "distinct_rated_opponents": 100,
      "draws": 113,
      "entry_count": 12,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:55:09Z",
      "losses": 132,
      "max_score": 68.09932142027597,
      "measured_at": null,
      "min_score": 18.014153696699164,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.17126791969,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.6511401212143,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19,
      "attempted_matches": 1197,
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 57
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.25293804044999996,
        "mean": 0.19953128278324997,
        "median": 0.20662718916666667,
        "min": 0.13279406625,
        "recorded_attempt_count": 57,
        "run_count": 27,
        "total": 5.24138213703
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": 41.614377784832975,
      "contributing_entrants": null,
      "distinct_rated_opponents": 599,
      "draws": 428,
      "entry_count": 19,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.037037037037037035,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:55:02Z",
      "losses": 392,
      "max_score": 57.31929094075836,
      "measured_at": null,
      "min_score": 29.39591170776535,
      "model_code_failure_rate": 0.2962962962962963,
      "model_code_failures": 8,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 0.7037037037037037,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1197,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.36299190223,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 18,
      "repaired_rate": 0.6666666666666666,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 38.11455597169624,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 377
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "max": 0.04815395,
        "mean": 0.0408814375,
        "median": 0.040641,
        "min": 0.0341807,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.654103
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.20768319617477,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 232,
      "entry_count": 16,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T04:34:09Z",
      "losses": 230,
      "max_score": 54.39524382491415,
      "measured_at": null,
      "min_score": 25.068514273806112,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.0836370972834,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": 16,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 37.20768319617477,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 700,
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 26
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.015971877,
        "mean": 0.00979196948,
        "median": 0.009500477,
        "min": 0.003562685,
        "recorded_attempt_count": 26,
        "run_count": 15,
        "total": 0.14255357568
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 37.746016066935304,
      "contributing_entrants": null,
      "distinct_rated_opponents": 350,
      "draws": 182,
      "entry_count": 11,
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "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
      },
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:47:12Z",
      "losses": 312,
      "max_score": 49.93322035186378,
      "measured_at": null,
      "min_score": 29.692155158998496,
      "model_code_failure_rate": 0.26666666666666666,
      "model_code_failures": 4,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.7333333333333333,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.8639466038817,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": 6,
      "repaired_rate": 0.4,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 34.9298304006065,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 202,
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.01660212,
        "mean": 0.00855959175,
        "median": 0.005979701,
        "min": 0.00271606,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.068476734
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.71387606868023,
      "contributing_entrants": null,
      "distinct_rated_opponents": 101,
      "draws": 150,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:46:17Z",
      "losses": 104,
      "max_score": 61.50686447534633,
      "measured_at": null,
      "min_score": 18.82577587485795,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.826713868567,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 29.976345822769016,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7,
      "attempted_matches": 252,
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0056201515,
        "mean": 0.0029446039375,
        "median": 0.001956843,
        "min": 0.001266762,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.029176983000000004
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 29.440367187054477,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 130,
      "entry_count": 14,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:15:48Z",
      "losses": 209,
      "max_score": 51.81286686979948,
      "measured_at": null,
      "min_score": 17.993252641418948,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.5204361339454,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.64757882677474,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 147
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 188,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.08193244999999999,
        "mean": 0.05495368125,
        "median": 0.056941025,
        "min": 0.02174195,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.43962945
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.017555673697316,
      "contributing_entrants": null,
      "distinct_rated_opponents": 94,
      "draws": 59,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:46:13Z",
      "losses": 179,
      "max_score": 41.14537153635741,
      "measured_at": null,
      "min_score": 19.747298274267855,
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.8647719765709,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 27.57894030213595,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 167,
      "capped_draws": 29,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.0264053125,
        "median": 0.022682375,
        "min": 0.01946775,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.2112425
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.04212337597506,
      "contributing_entrants": null,
      "distinct_rated_opponents": 84,
      "draws": 106,
      "entry_count": 10,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:34:29Z",
      "losses": 169,
      "max_score": 37.72719101235718,
      "measured_at": null,
      "min_score": 16.251044990851373,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 167,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.942761941479,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 24.044225601614347,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 333,
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.039679950000000005,
        "mean": 0.029276065625,
        "median": 0.0306386,
        "min": 0.01864685,
        "recorded_attempt_count": 33,
        "run_count": 16,
        "total": 0.46841705000000006
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.44908019609191,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 294,
      "entry_count": 18,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:46:59Z",
      "losses": 193,
      "max_score": 32.441158944802936,
      "measured_at": null,
      "min_score": 24.546803091037,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.4594864632938,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 23.771600760331932,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.341716425,
        "mean": 0.30867194062500003,
        "median": 0.31836633750000004,
        "min": 0.2745495,
        "recorded_attempt_count": 33,
        "run_count": 16,
        "total": 4.9387510500000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 62.82337105668461,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 106,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T05:19:08Z",
      "losses": 59,
      "max_score": 90.24764585966038,
      "measured_at": null,
      "min_score": 35.39909625370884,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 8,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.5,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.2287904366156,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": 8,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 52.82794751572005,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 158,
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.055222,
        "mean": 0.046879,
        "median": 0.046959,
        "min": 0.039474,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.375032
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.58771087910249,
      "contributing_entrants": null,
      "distinct_rated_opponents": 79,
      "draws": 12,
      "entry_count": 8,
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "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
      },
      "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": "2026-07-27T15:55:08Z",
      "losses": 136,
      "max_score": 51.34913352806587,
      "measured_at": null,
      "min_score": 36.12527583054917,
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.0725512767813,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 45.06171397988976,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.213668025,
        "mean": 0.180929025625,
        "median": 0.1746528825,
        "min": 0.16318875,
        "recorded_attempt_count": 37,
        "run_count": 16,
        "total": 2.8948644100000003
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 44.11619405789825,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 73,
      "entry_count": 5,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-26T02:15:57Z",
      "losses": 80,
      "max_score": 56.06167167227131,
      "measured_at": null,
      "min_score": 21.717457965632377,
      "model_code_failure_rate": 0.6875,
      "model_code_failures": 11,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "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": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.5821063001963,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 32.984548508298495,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 5,
      "attempted_matches": 210,
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 105,
      "draws": 141,
      "entry_count": 5,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T15:40:08Z",
      "losses": 44,
      "max_score": 51.785443642756896,
      "measured_at": null,
      "min_score": 21.77927935287923,
      "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": "provisional",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3539522692658,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 31.789261679901063,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 142,
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.33185775,
        "mean": 0.18266821875,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 1.7932034999999995
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.868711903025027,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 19,
      "entry_count": 8,
      "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
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-27T11:30:30Z",
      "losses": 195,
      "max_score": 28.913374800215543,
      "measured_at": null,
      "min_score": 15.499927748138225,
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.8775248484535,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "track",
      "score": 17.8557284981134,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:16Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1904.3194643073384,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:16Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.2827891456054,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 77.04163766987543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T10:47:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.2957199694602,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 75.64277085800467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T10:48:01Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.604801686931,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.15810496914253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 98,
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 49,
      "draws": 34,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.62225026505,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.73590439615545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.97783371817835,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:34Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.161593705389,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 64.35576459451039,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.289805193975,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.48880272697796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:30Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.5380641852346,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.81280359013286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.6415648788145,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.06172320072071,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 44
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 128,
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 64,
      "draws": 51,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.68828391194,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.45198302770152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.13401041481541,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:59:11Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.3730974136329,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.16535532101704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:45:00Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.3715719552615,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.81286686979948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 68,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:55:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.216784303636,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.62917908688148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-07-27T10:47:58Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.114031725191,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.66102087130642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-26T04:33:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6576382024014,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.65575530999811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:45Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2237959132,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.5724430344671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:47:44Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.4008078994289,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.20979035442635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:15Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.9172858681118,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.327363323089216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.7562594006596,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T04:31:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.3176275999922,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.001139620161496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 18,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.190176438217,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.28492958888438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.19324853318743,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-07-27T11:47:56Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.0645693107565,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.53737468779395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T10:51:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.60640070509,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.776628277424983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.80145244019624,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:24Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.1499854705874,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.77927935287923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T10:50:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.5005645283743,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 19.747298274267855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:50Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1778.6483184624055,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:56Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.1613209336665,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 90.09571894996164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 19,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:50Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.158468705878,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 78.54184751328685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T15:20:16Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.515391796302,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 73.19703425601392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:54Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.2143177522778,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.273546807227696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:04Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.3008269640052,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.45287871885732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 39,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T07:55:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1746719119114,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.748923171140326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 33,
      "draws": 79,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T15:22:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.1302271015347,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.890496423277526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.4017714074875,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 116,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T11:23:13Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.5867943828466,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.985200935164713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.61455287691689,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 104,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:00Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.7128017422178,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.692155158998496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.80644772842997,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 175,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 88,
      "draws": 146,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:58Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 175,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.7873247436503,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.39591170776535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.200730137000697,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "draws": 105,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:54Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.01344851071,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.93961926553232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 73,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-26T04:32:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.683594336881,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.548198358769575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.75968834662516,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.0639451591423,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.146372762679754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:53Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.57787505147,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.542272343102017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 44.39456088374059,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 106,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 53,
      "draws": 169,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:05Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8761702774934,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.32744061084774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.39228737690977,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:42Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4827683360977,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.675502781911693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.31407690254356,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 74,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 37,
      "draws": 113,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:56Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.9285932914202,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.35927855243578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 45.01309903675748,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-26T02:14:07Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.91270724254,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.858580155536725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 64,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.958193352233,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 20.82093118555568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 53,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:01Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.505213110513,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.82577587485795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.19324853318743,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:07Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1819.3735501939025,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 99.01750849232472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T08:03:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.207188118948,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.09760234044293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:28Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.350902249458,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.14974362057465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 11,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.6158310169712,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.67575600395128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T10:18:25Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 39,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.6990353724188,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.27053092873559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 35.30694150420948,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-26T02:12:12Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9062245881858,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.42582526757698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 35,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.4987104220186,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.0058977081419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 61.71645590010924,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 96,
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 48,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:17Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.572800589371,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.7143796127683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T08:02:37Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.3469365962942,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.329296821438945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 52.64737393979195,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 124,
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 62,
      "draws": 46,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T11:48:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8677869593969,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.63731750642038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.435575077886185,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:02Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 21,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.6707577765233,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.7702372055603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 59.5501790889026,
      "unilateral_faults": 1,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 14,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T10:18:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0530820785134,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 38.82631568621353,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 23,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T02:18:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.3679574628934,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.706944523905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:15Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.3051991222185,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.39410414668713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 17,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T10:19:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.099303746516,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.63120574976151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:49Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1821.3947826255776,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 20,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:00Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.9563654007216,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 73.33281812779559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-26T05:17:50Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.9321943610776,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.37465172530936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 26,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.789369331552,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.43667406598968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T10:35:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.2220685254226,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.3067010884318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:09:56Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.4078028250656,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.43603009561291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 27,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T10:30:15Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.4093381266223,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.412604814752626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 19
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 94,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 47,
      "draws": 77,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:46Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.0760172985165,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.17117874326892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.49878111612754,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T10:29:48Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.9773873174586,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.2849917916824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 33,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:46Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.736546987583,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 39.29062220793382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 30,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:33:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9190911735002,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 33.302708753199845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 82,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:22:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4789629339475,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.86936940191663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.03477987847802,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.4284617057842,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.510166457816872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:49Z",
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.3598482849127,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.921753926830576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 28,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 43,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:55Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.450385706255,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.996130934586745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:06Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2980270082412,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.837372334700223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.62023516889464,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 41,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-07-27T11:18:04Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.4129665430028,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.735143570454905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.9056700157024,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 37,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T15:34:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.351636088787,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.30965713552444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 60.027768011903404,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-26T02:19:07Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.5657189380322,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.068514273806112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 50,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:10:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.4221707921552,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.588513823342623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 22,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T10:34:01Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.214332474687,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 23.27152769675579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.67857142857143,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 39,
      "draws": 108,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-27T15:31:27Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.3641057916232,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.82665639057853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.908551952141345,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 16,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:17:57Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6129486635432,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.637247385879313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 49.76941398892446,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 36,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T00:21:27Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5853927038256,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 17.993252641418948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 60.027768011903404,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1933.7094741760584,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 96.57379066170128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.678809124274,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 92.3708669015868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:29Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1859.1162007965604,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 86.37300771504712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:30Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1822.9563803754577,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 83.82486081338791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-26T05:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1807.478590078014,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.52103910064591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:20Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1760.1833865422625,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.6585459712308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:26Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.892992498132,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.56906281561947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.9193174279271,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.024239354593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 137,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:49Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 137,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.7103540889234,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 59.786700401424746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.22717850480214,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:33Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.9630027424323,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.44226639021666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T10:38:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.596774461676,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.00415603353663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.6378956784858,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.35911215449047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:21Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.8716690403694,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.2770740935357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.0151173817317,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 50.53327801033048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 86,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:33Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.9682819146449,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.87639190655733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.46393572312315,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 210,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 105,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-07-27T11:26:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.623822330184,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 48.517867682604326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.625289791427727,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 97,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 97,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.7035184605436,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.80140024106329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.11849350131416,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:12Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.29536649102,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 46.232953795131394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.699748644724702,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:09Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.9038956193683,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.11609569421241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 44.39456088374059,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:08Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.1170634631212,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.73585500348754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.2356618633981,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:19Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0856341696644,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 41.14537153635741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.70587299553475,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 71,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8705390548175,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.15666178716489,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.179828253878972,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 76,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-27T15:46:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.3047231017686,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.441158944802936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.253662717865495,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-26T01:24:23Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.323659481682,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.68905148984333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-26T02:19:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.8823575046931,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.62168789866385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:30Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.784860201679,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.284916786321386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.80145244019624,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-07-27T11:30:34Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.0234481385794,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 16.251044990851373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 44.39456088374059,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-26T05:19:08Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.502473660851,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 90.24764585966038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:35Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1779.224826819665,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 89.6862854041758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:44Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1718.0303169897015,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 82.20988966457762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:35Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.5493909205152,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 80.12004893199418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:32Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.484096247477,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 79.72428872775545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:17Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.7457177478934,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 78.42707203303546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:21Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.089981134785,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.4748305783871,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:45:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1676.3558507059174,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 76.11062624621614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:51Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.2207187307338,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 71.69384651100232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 36,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.9657064331486,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.79293959997881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:08Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.082997776762,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 69.153570024744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.2514891902983,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 68.09932142027597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 43.7735813706023,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.9904173149405,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.786908880400794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 40.79847712741413,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 3,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.710166277599,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.50686447534633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.95999312316211,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 8,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.531656885091,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.3837110637506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 138,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 69,
      "draws": 13,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:16Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.2640974459423,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.081285429963856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 35.315587721029885,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-26T01:20:52Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.3338889332665,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 56.06167167227131,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T15:26:03Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.0458901456975,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.76800622889098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-26T04:34:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.088754825532,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.39524382491415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 6,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-27T15:24:33Z",
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.76159895558,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.785443642756896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.8121397572054,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.03659155745648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.60745956276516,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 35,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 4,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:37:14Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.8609860751917,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 45.237594115915286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.817992173360395,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T11:53:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.4552403692137,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.10102860564115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 36,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T11:46:13Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.4926583834322,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.244509748458896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 45.462269258808135,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 35,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 18,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T15:27:32Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.51918938241,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.791817765880385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 37.948705117938445,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-27T15:29:50Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.5600157396711,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 30.620679713560136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.355683254666296,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-27T10:45:10Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.670844139026,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.913374800215543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 34,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 17,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-07-27T10:45:13Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.332669440063,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 28.544824407056502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 37.551153208577354,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-26T05:16:44Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1910.1513048995253,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 98.99816924724276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.7924577346591,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 91.89097628140996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:02Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.87837198572,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 88.02796582947613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-27T15:17:48Z",
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.24753254842,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 72.0322843616957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 63,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:00Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.6855421123205,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 66.08919562986975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.755723064737715,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:00Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6157786139568,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.912194201697034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.730475331812,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 62.90248060999168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:24Z",
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.40868111242,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 61.39391405879897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:53Z",
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.641725509094,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 60.13352254421294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 34
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 118,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-07-27T15:57:47Z",
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.3056410970028,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 58.63055697544416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.090637048514616,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 214,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:52Z",
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.4603703334396,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 57.31929094075836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.334374414189384,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.584014782258,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 55.327402124523715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:55Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.1316071761985,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 54.36584442360475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 50
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 140,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 70,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.293623643294,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 53.42069139868415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 31.933316946790622,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-07-27T11:54:22Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.8649438145444,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 52.53268699210788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.815994700812965,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:20Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.9260778582047,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 49.93322035186378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.267903630526114,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:05Z",
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9594139977837,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 47.34867560826997,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.320314512178,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 44.8546337721922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:53Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.0948620707277,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.72719101235718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.3656681646023,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 37.12643857527608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6260556799098,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 36.12527583054917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:58Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.2392931700497,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.91319206814089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 46.28203845127178,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-26T02:15:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.587035593027,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 32.59598125820875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:15:48Z",
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.7298482608094,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.031275607799287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:52Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.71662390316,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 29.094119565026094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 41.18336395796551,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:55Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.4479943480187,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 15.499927748138225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.80145244019624,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 1,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:56Z",
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1912.1873848057296,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 9,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:02Z",
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.1796710479507,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.76630327200057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:50Z",
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.1260261745642,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 65.02884715553996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 114,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 6,
      "distinct_rated_opponents": 57,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-07-27T11:07:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.9837411017909,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.66486562803726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.178218158143345,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 80,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:46Z",
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1689.6876237550243,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 63.475663086016624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 2,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:56Z",
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.734946206889,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 51.34913352806587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 10,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-07-27T15:55:10Z",
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.5237946011143,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.85247714738262,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 5,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.27072293001,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 43.70296063793118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 216,
      "capped_draws": 107,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 108,
      "draws": 107,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-27T15:47:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.60438067143,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 42.36624656479914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.80281801640143,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 15,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T09:17:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.706490224709,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 40.47739221194158,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 38,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-26T05:18:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.7738994568635,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 35.39909625370884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.561240097148016,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 52,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:27Z",
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.812720862631,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 34.63468032269175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.036461425079892,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 42,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-27T15:56:30Z",
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.6642579295235,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.45351907819096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 10
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 198,
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 99,
      "draws": 88,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-07-27T11:06:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.680872206851,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 31.224440808203862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.42733990918024,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:26Z",
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.883097011328,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 27.30638809711645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 21,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-27T11:04:07Z",
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.793708185056,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 26.439052410696952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 36.2356618633981,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 48,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.1969593602666,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.746626341753977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 58,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-27T11:03:50Z",
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3808697764316,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.48617559035576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 39,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:08Z",
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4563174105635,
      "reasoning_level": "Highest",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": null,
          "requested_effort": "highest",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Highest",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Highest",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "highest"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.403373868757644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 65,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-26T02:17:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.564493870363,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 25.09160686347721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:39Z",
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.5283788982229,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.85647924437633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.941634169259466,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 44,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-27T15:40:00Z",
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.7730988237663,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.57930679395035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.48716501561997,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 84,
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 42,
      "draws": 109,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:44Z",
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0502690810122,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.546803091037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 39.34626684974488,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 69,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.7246740268902,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 24.13090597526191,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 33.54983807626827,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 88,
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 44,
      "draws": 103,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-07-27T11:05:59Z",
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.93041194247,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 22.515456529989933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.11029391633042,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 32,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-26T02:14:59Z",
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.7532402504671,
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 21.717457965632377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 38,
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 19,
      "draws": 54,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-27T10:59:21Z",
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.1765488406536,
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 18.014153696699164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.53975118769762,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 12,
      "entry_count": null,
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-07-27T10:53:25Z",
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.9378527645924,
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "legacy_reasoning_presets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260727-4d94e2ae1be2",
      "row_kind": "game",
      "score": 15.99986870925893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9",
      "snapshot_id": "20260727_194501",
      "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": 20
    }
  ],
  "schema_version": 8,
  "snapshot_id": "20260727_194501",
  "suite_line_id": "gamebench2",
  "suite_version": "2-known8-r3"
}